Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.4354. Min Act: -0.1700
Data Index: 575411 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.3883. Min Act: -0.1700
Data Index: 5611463 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.3570. Min Act: -0.1700
Data Index: 958036 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.3413. Min Act: -0.1700
Data Index: 8192400 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.3099. Min Act: -0.1700
Data Index: 865748 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.3256. Min Act: -0.1700
Data Index: 485588 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.2942. Min Act: -0.1700
Data Index: 2748233 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.2471. Min Act: -0.1700
Data Index: 2708799 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.2314. Min Act: -0.1700
Data Index: 1041952 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.2314. Min Act: -0.1700
Data Index: 3323387 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.2471. Min Act: -0.1700
Data Index: 2829108 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.2157. Min Act: -0.1700
Data Index: 1934962 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1999. Min Act: -0.1700
Data Index: 6231187 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1999. Min Act: -0.1700
Data Index: 7622108 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1999. Min Act: -0.1700
Data Index: 2456551 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1842. Min Act: -0.1700
Data Index: 6069099 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1999. Min Act: -0.1700
Data Index: 1699563 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1842. Min Act: -0.1700
Data Index: 760021 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1527. Min Act: -0.1700
Data Index: 2882414 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4354. Min Range: -3.4354
Max Act: 3.1527. Min Act: -0.1700
Data Index: 5794633 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19