Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.9494. Min Act: -0.1700
Data Index: 5572216 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.9494. Min Act: -0.1700
Data Index: 7526150 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.8244. Min Act: -0.1700
Data Index: 4567311 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.6369. Min Act: -0.1700
Data Index: 3367459 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.6369. Min Act: -0.1700
Data Index: 5973722 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.5119. Min Act: -0.1700
Data Index: 6333968 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.3869. Min Act: -0.1700
Data Index: 3255905 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.2619. Min Act: -0.1700
Data Index: 4795978 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.2619. Min Act: -0.1700
Data Index: 6333969 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.1994. Min Act: -0.1700
Data Index: 8478833 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.1994. Min Act: -0.1700
Data Index: 2578942 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.0744. Min Act: -0.1700
Data Index: 6194769 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.0744. Min Act: -0.1700
Data Index: 5474827 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.1369. Min Act: -0.1700
Data Index: 3374028 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.0744. Min Act: -0.1700
Data Index: 4045628 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9494. Min Range: -10.9494
Max Act: 10.0119. Min Act: -0.1700
Data Index: 7035478 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9494. Min Range: -10.9494
Max Act: 9.9494. Min Act: -0.1700
Data Index: 5791318 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9494. Min Range: -10.9494
Max Act: 9.9494. Min Act: -0.1700
Data Index: 6384723 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9494. Min Range: -10.9494
Max Act: 9.8869. Min Act: -0.1700
Data Index: 5878119 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9494. Min Range: -10.9494
Max Act: 9.8244. Min Act: -0.1700
Data Index: 5302812 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19