Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0974. Min Range: -7.0974
Max Act: 7.0974. Min Act: -0.1700
Data Index: 2101689 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0974. Min Range: -7.0974
Max Act: 7.0349. Min Act: -0.1700
Data Index: 3983580 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0974. Min Range: -7.0974
Max Act: 7.0349. Min Act: -0.1700
Data Index: 1022946 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0974. Min Range: -7.0974
Max Act: 7.0036. Min Act: -0.1700
Data Index: 6561154 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.9411. Min Act: -0.1700
Data Index: 6820878 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.8474. Min Act: -0.1700
Data Index: 8180987 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.8161. Min Act: -0.1700
Data Index: 629925 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7849. Min Act: -0.1700
Data Index: 6287242 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7536. Min Act: -0.1700
Data Index: 2997995 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7536. Min Act: -0.1700
Data Index: 8326228 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7536. Min Act: -0.1700
Data Index: 2216943 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7224. Min Act: -0.1700
Data Index: 2311759 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.6911. Min Act: -0.1700
Data Index: 5288693 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7536. Min Act: -0.1700
Data Index: 2216942 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7224. Min Act: -0.1700
Data Index: 643758 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.6911. Min Act: -0.1700
Data Index: 4034436 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.6911. Min Act: -0.1700
Data Index: 1065647 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.6911. Min Act: -0.1700
Data Index: 648908 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.7224. Min Act: -0.1700
Data Index: 4271622 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0974. Min Range: -7.0974
Max Act: 6.6911. Min Act: -0.1700
Data Index: 2909419 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19