Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.3974. Min Act: -0.1700
Data Index: 1554965 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.3974. Min Act: -0.1700
Data Index: 4571189 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.3349. Min Act: -0.1700
Data Index: 3231827 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.3349. Min Act: -0.1700
Data Index: 5941025 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.3349. Min Act: -0.1700
Data Index: 6527390 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.3036. Min Act: -0.1700
Data Index: 3321754 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.3036. Min Act: -0.1700
Data Index: 7668327 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.2724. Min Act: -0.1700
Data Index: 8419731 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.2724. Min Act: -0.1700
Data Index: 3990953 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.2724. Min Act: -0.1700
Data Index: 8304148 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.2411. Min Act: -0.1700
Data Index: 1797389 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.2099. Min Act: -0.1700
Data Index: 7280274 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.2099. Min Act: -0.1700
Data Index: 63418 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.2099. Min Act: -0.1700
Data Index: 7519286 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.1786. Min Act: -0.1700
Data Index: 7346481 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.1786. Min Act: -0.1700
Data Index: 360584 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.1786. Min Act: -0.1700
Data Index: 5123342 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.1474. Min Act: -0.1700
Data Index: 699066 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.1474. Min Act: -0.1700
Data Index: 4933800 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3974. Min Range: -6.3974
Max Act: 6.1161. Min Act: -0.1700
Data Index: 7114932 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19