Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.8685. Min Act: -0.1700
Data Index: 5009583 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.8060. Min Act: -0.1700
Data Index: 3887162 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.5560. Min Act: -0.1700
Data Index: 8514326 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.4310. Min Act: -0.1700
Data Index: 6623130 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.3060. Min Act: -0.1700
Data Index: 4781991 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.3060. Min Act: -0.1700
Data Index: 3887620 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.2435. Min Act: -0.1700
Data Index: 8029484 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.2435. Min Act: -0.1700
Data Index: 1484388 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1810. Min Act: -0.1700
Data Index: 567677 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1810. Min Act: -0.1700
Data Index: 6058112 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1810. Min Act: -0.1700
Data Index: 6189398 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1810. Min Act: -0.1700
Data Index: 6426747 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1810. Min Act: -0.1700
Data Index: 1418530 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1185. Min Act: -0.1700
Data Index: 8608135 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.0560. Min Act: -0.1700
Data Index: 6149375 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1185. Min Act: -0.1700
Data Index: 6415201 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1185. Min Act: -0.1700
Data Index: 2011809 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.1185. Min Act: -0.1700
Data Index: 6827289 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.0560. Min Act: -0.1700
Data Index: 380847 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8685. Min Range: -8.8685
Max Act: 8.0560. Min Act: -0.1700
Data Index: 5507537 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19