Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1204 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3038. Min Range: -7.3038
Max Act: 7.3038. Min Act: -0.1700
Data Index: 934233 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3038. Min Range: -7.3038
Max Act: 7.1788. Min Act: -0.1700
Data Index: 6349129 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3038. Min Range: -7.3038
Max Act: 7.0851. Min Act: -0.1700
Data Index: 8657817 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.9601. Min Act: -0.1700
Data Index: 5283665 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.9288. Min Act: -0.1700
Data Index: 2516390 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8976. Min Act: -0.1700
Data Index: 7012279 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8663. Min Act: -0.1700
Data Index: 1537878 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8663. Min Act: -0.1700
Data Index: 7640787 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8351. Min Act: -0.1700
Data Index: 2588587 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8351. Min Act: -0.1700
Data Index: 6585223 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8038. Min Act: -0.1700
Data Index: 3098773 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8038. Min Act: -0.1700
Data Index: 627246 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8038. Min Act: -0.1700
Data Index: 1614116 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.7726. Min Act: -0.1700
Data Index: 6410583 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8038. Min Act: -0.1700
Data Index: 2235346 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.8038. Min Act: -0.1700
Data Index: 7530216 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.7413. Min Act: -0.1700
Data Index: 6433116 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.7413. Min Act: -0.1700
Data Index: 6320278 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.7726. Min Act: -0.1700
Data Index: 6744086 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3038. Min Range: -7.3038
Max Act: 6.7413. Min Act: -0.1700
Data Index: 4218591 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19