Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3957. Min Act: -0.1700
Data Index: 4026324 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3957. Min Act: -0.1700
Data Index: 131756 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3957. Min Act: -0.1700
Data Index: 1884263 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3794. Min Act: -0.1700
Data Index: 4688669 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3630. Min Act: -0.1700
Data Index: 5954940 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3466. Min Act: -0.1700
Data Index: 8723406 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3466. Min Act: -0.1700
Data Index: 1095733 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3466. Min Act: -0.1700
Data Index: 5618723 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3302. Min Act: -0.1700
Data Index: 6146621 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3138. Min Act: -0.1700
Data Index: 5352435 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3302. Min Act: -0.1700
Data Index: 5369721 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3302. Min Act: -0.1700
Data Index: 5174030 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3138. Min Act: -0.1700
Data Index: 2385916 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3302. Min Act: -0.1700
Data Index: 3132775 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.2974. Min Act: -0.1700
Data Index: 5442564 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.3138. Min Act: -0.1700
Data Index: 2279201 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.2974. Min Act: -0.1700
Data Index: 4688670 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.2974. Min Act: -0.1700
Data Index: 8224505 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.2974. Min Act: -0.1700
Data Index: 8710875 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3957. Min Range: -2.3957
Max Act: 2.2809. Min Act: -0.1700
Data Index: 5015317 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19