Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.9066. Min Act: -0.1700
Data Index: 6145829 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.8441. Min Act: -0.1700
Data Index: 3430134 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.7191. Min Act: -0.1700
Data Index: 2493513 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.6566. Min Act: -0.1700
Data Index: 7454287 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.6566. Min Act: -0.1700
Data Index: 3057949 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.6566. Min Act: -0.1700
Data Index: 1020382 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5941. Min Act: -0.1700
Data Index: 6085122 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5941. Min Act: -0.1700
Data Index: 6259390 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5941. Min Act: -0.1700
Data Index: 6567044 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5941. Min Act: -0.1700
Data Index: 4750216 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5941. Min Act: -0.1700
Data Index: 975750 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5941. Min Act: -0.1700
Data Index: 4824475 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5316. Min Act: -0.1700
Data Index: 6990059 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.4691. Min Act: -0.1700
Data Index: 999164 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5316. Min Act: -0.1700
Data Index: 8666394 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5316. Min Act: -0.1700
Data Index: 3210140 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.5316. Min Act: -0.1700
Data Index: 2321479 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.4691. Min Act: -0.1700
Data Index: 6347674 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.4691. Min Act: -0.1700
Data Index: 376416 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9066. Min Range: -10.9066
Max Act: 10.4691. Min Act: -0.1700
Data Index: 7997178 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19