Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2319. Min Range: -6.2319
Max Act: 6.2319. Min Act: -0.1700
Data Index: 3664014 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2319. Min Range: -6.2319
Max Act: 6.1069. Min Act: -0.1700
Data Index: 8511582 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2319. Min Range: -6.2319
Max Act: 6.0757. Min Act: -0.1700
Data Index: 7523377 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2319. Min Range: -6.2319
Max Act: 6.0444. Min Act: -0.1700
Data Index: 8660627 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2319. Min Range: -6.2319
Max Act: 6.0132. Min Act: -0.1700
Data Index: 1223028 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2319. Min Range: -6.2319
Max Act: 6.0444. Min Act: -0.1700
Data Index: 5555223 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.9819. Min Act: -0.1700
Data Index: 1538414 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.9507. Min Act: -0.1700
Data Index: 1694203 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.9819. Min Act: -0.1700
Data Index: 6289847 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.9819. Min Act: -0.1700
Data Index: 7354289 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.9194. Min Act: -0.1700
Data Index: 3496064 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.9194. Min Act: -0.1700
Data Index: 519153 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8882. Min Act: -0.1700
Data Index: 1090698 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8882. Min Act: -0.1700
Data Index: 448141 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8882. Min Act: -0.1700
Data Index: 6851412 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8882. Min Act: -0.1700
Data Index: 7073103 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8882. Min Act: -0.1700
Data Index: 4114982 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8569. Min Act: -0.1700
Data Index: 6844407 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8569. Min Act: -0.1700
Data Index: 1526246 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2319. Min Range: -6.2319
Max Act: 5.8257. Min Act: -0.1700
Data Index: 6356567 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19