Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.6912. Min Act: -0.1700
Data Index: 1712666 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.5975. Min Act: -0.1700
Data Index: 8533352 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.5350. Min Act: -0.1700
Data Index: 7752677 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.4725. Min Act: -0.1700
Data Index: 7916543 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.4100. Min Act: -0.1700
Data Index: 3085098 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.4100. Min Act: -0.1700
Data Index: 975785 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.3787. Min Act: -0.1700
Data Index: 6568733 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.3787. Min Act: -0.1700
Data Index: 8232950 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.3787. Min Act: -0.1700
Data Index: 1450983 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.3475. Min Act: -0.1700
Data Index: 3100861 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.3162. Min Act: -0.1700
Data Index: 5369823 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.3162. Min Act: -0.1700
Data Index: 4229800 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2850. Min Act: -0.1700
Data Index: 3294870 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2850. Min Act: -0.1700
Data Index: 7812440 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2850. Min Act: -0.1700
Data Index: 1839556 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2537. Min Act: -0.1700
Data Index: 1484143 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2537. Min Act: -0.1700
Data Index: 2065175 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2225. Min Act: -0.1700
Data Index: 1502954 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2225. Min Act: -0.1700
Data Index: 1994100 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6912. Min Range: -6.6912
Max Act: 6.2225. Min Act: -0.1700
Data Index: 3007753 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19