Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1153 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4085. Min Range: -6.4085
Max Act: 6.4085. Min Act: -0.1700
Data Index: 2683296 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4085. Min Range: -6.4085
Max Act: 6.2210. Min Act: -0.1700
Data Index: 3780805 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4085. Min Range: -6.4085
Max Act: 6.1585. Min Act: -0.1700
Data Index: 7588251 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4085. Min Range: -6.4085
Max Act: 6.1585. Min Act: -0.1700
Data Index: 1240916 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4085. Min Range: -6.4085
Max Act: 6.0647. Min Act: -0.1700
Data Index: 4602665 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4085. Min Range: -6.4085
Max Act: 6.0335. Min Act: -0.1700
Data Index: 785030 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.9710. Min Act: -0.1700
Data Index: 7450927 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.9397. Min Act: -0.1700
Data Index: 3912885 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.9085. Min Act: -0.1700
Data Index: 651949 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.9085. Min Act: -0.1700
Data Index: 886654 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8772. Min Act: -0.1700
Data Index: 3224856 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.9085. Min Act: -0.1700
Data Index: 5433036 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8772. Min Act: -0.1700
Data Index: 4432073 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8772. Min Act: -0.1700
Data Index: 4729422 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8772. Min Act: -0.1700
Data Index: 2281109 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8460. Min Act: -0.1700
Data Index: 4006401 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5054580 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5767007 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8147. Min Act: -0.1700
Data Index: 2755188 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4085. Min Range: -6.4085
Max Act: 5.8147. Min Act: -0.1700
Data Index: 1050656 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19