Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1990 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.3145. Min Act: -0.1700
Data Index: 2573655 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.2520. Min Act: -0.1700
Data Index: 1914952 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.2520. Min Act: -0.1700
Data Index: 149190 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.1895. Min Act: -0.1700
Data Index: 7317882 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.1270. Min Act: -0.1700
Data Index: 7189004 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.0645. Min Act: -0.1700
Data Index: 6272378 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.0020. Min Act: -0.1700
Data Index: 4210437 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.0020. Min Act: -0.1700
Data Index: 1457876 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.0020. Min Act: -0.1700
Data Index: 2535834 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.0020. Min Act: -0.1700
Data Index: 5432927 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.0020. Min Act: -0.1700
Data Index: 1770162 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3145. Min Range: -8.3145
Max Act: 8.0020. Min Act: -0.1700
Data Index: 1630279 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 2000123 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 4307425 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 5899575 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 4699201 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 6477661 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 3576043 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 6742070 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3145. Min Range: -8.3145
Max Act: 7.9395. Min Act: -0.1700
Data Index: 4724237 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19