Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.9773. Min Act: -0.1700
Data Index: 5466822 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.8523. Min Act: -0.1700
Data Index: 321497 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.8211. Min Act: -0.1700
Data Index: 4321522 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.7898. Min Act: -0.1700
Data Index: 3185170 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.7898. Min Act: -0.1700
Data Index: 3404751 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.7273. Min Act: -0.1700
Data Index: 7998756 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6961. Min Act: -0.1700
Data Index: 1037419 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6648. Min Act: -0.1700
Data Index: 393366 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6336. Min Act: -0.1700
Data Index: 1022031 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6336. Min Act: -0.1700
Data Index: 4519911 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6023. Min Act: -0.1700
Data Index: 7054624 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6023. Min Act: -0.1700
Data Index: 7649917 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6023. Min Act: -0.1700
Data Index: 5305426 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.5711. Min Act: -0.1700
Data Index: 3275012 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.6023. Min Act: -0.1700
Data Index: 3558973 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.5711. Min Act: -0.1700
Data Index: 8016706 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.5398. Min Act: -0.1700
Data Index: 2218897 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.5711. Min Act: -0.1700
Data Index: 6538802 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.5398. Min Act: -0.1700
Data Index: 265920 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9773. Min Range: -6.9773
Max Act: 6.5398. Min Act: -0.1700
Data Index: 6900172 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19