Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3237 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.6466. Min Act: -0.1700
Data Index: 5461691 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.3341. Min Act: -0.1700
Data Index: 258804 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.2716. Min Act: -0.1700
Data Index: 7355290 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.1466. Min Act: -0.1700
Data Index: 6089699 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.1466. Min Act: -0.1700
Data Index: 2726664 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.1466. Min Act: -0.1700
Data Index: 284575 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.0841. Min Act: -0.1700
Data Index: 133051 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.0216. Min Act: -0.1700
Data Index: 7714546 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.0216. Min Act: -0.1700
Data Index: 4972413 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.0216. Min Act: -0.1700
Data Index: 2336808 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6466. Min Range: -8.6466
Max Act: 8.0216. Min Act: -0.1700
Data Index: 7832722 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.9591. Min Act: -0.1700
Data Index: 822320 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 3132229 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 5830824 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8654. Min Act: -0.1700
Data Index: 4180922 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8654. Min Act: -0.1700
Data Index: 4946627 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 3273841 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8341. Min Act: -0.1700
Data Index: 3869540 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8029. Min Act: -0.1700
Data Index: 3806687 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6466. Min Range: -8.6466
Max Act: 7.8029. Min Act: -0.1700
Data Index: 3353069 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19