Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.7476. Min Act: -0.1700
Data Index: 320801 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.6851. Min Act: -0.1700
Data Index: 4599162 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7037040 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.5914. Min Act: -0.1700
Data Index: 3394344 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.5914. Min Act: -0.1700
Data Index: 3201565 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.5601. Min Act: -0.1700
Data Index: 2308030 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3740766 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.5289. Min Act: -0.1700
Data Index: 7207075 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.4976. Min Act: -0.1700
Data Index: 2736304 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.4976. Min Act: -0.1700
Data Index: 2921533 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.4351. Min Act: -0.1700
Data Index: 1835884 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.4351. Min Act: -0.1700
Data Index: 6163921 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.4039. Min Act: -0.1700
Data Index: 1876847 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.4039. Min Act: -0.1700
Data Index: 2439608 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.4039. Min Act: -0.1700
Data Index: 6441197 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.3414. Min Act: -0.1700
Data Index: 8104866 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.3414. Min Act: -0.1700
Data Index: 324872 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.3726. Min Act: -0.1700
Data Index: 7976410 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.2789. Min Act: -0.1700
Data Index: 1828895 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7476. Min Range: -6.7476
Max Act: 6.3101. Min Act: -0.1700
Data Index: 6301202 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19