Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.6143. Min Act: -0.1700
Data Index: 8582863 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.5518. Min Act: -0.1700
Data Index: 5646137 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.5518. Min Act: -0.1700
Data Index: 2142543 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.5518. Min Act: -0.1700
Data Index: 8735669 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.5518. Min Act: -0.1700
Data Index: 1806176 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.5518. Min Act: -0.1700
Data Index: 2142548 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4893. Min Act: -0.1700
Data Index: 8689285 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4893. Min Act: -0.1700
Data Index: 362898 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4893. Min Act: -0.1700
Data Index: 2832045 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4893. Min Act: -0.1700
Data Index: 8735664 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.5518. Min Act: -0.1700
Data Index: 6892838 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4893. Min Act: -0.1700
Data Index: 2142541 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 5178188 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 1188790 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 4086367 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 3237093 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 5070549 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 1257573 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 5912106 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6143. Min Range: -8.6143
Max Act: 8.4268. Min Act: -0.1700
Data Index: 336047 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19