Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6343. Min Range: -7.6343
Max Act: 7.6343. Min Act: -0.1700
Data Index: 1790308 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6343. Min Range: -7.6343
Max Act: 7.1031. Min Act: -0.1700
Data Index: 1686500 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.8843. Min Act: -0.1700
Data Index: 1988057 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.8531. Min Act: -0.1700
Data Index: 6224749 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.7593. Min Act: -0.1700
Data Index: 408876 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.7906. Min Act: -0.1700
Data Index: 1502749 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.7593. Min Act: -0.1700
Data Index: 2650968 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.7906. Min Act: -0.1700
Data Index: 5567579 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.7281. Min Act: -0.1700
Data Index: 5327623 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.7281. Min Act: -0.1700
Data Index: 4407815 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6968. Min Act: -0.1700
Data Index: 5787167 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6656. Min Act: -0.1700
Data Index: 480984 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7871143 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6656. Min Act: -0.1700
Data Index: 1697057 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6656. Min Act: -0.1700
Data Index: 3448788 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6656. Min Act: -0.1700
Data Index: 4759088 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7540545 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6343. Min Act: -0.1700
Data Index: 2285722 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6031. Min Act: -0.1700
Data Index: 6262807 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6343. Min Range: -7.6343
Max Act: 6.6031. Min Act: -0.1700
Data Index: 1897812 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19