Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.8346. Min Act: -0.1700
Data Index: 8287267 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.6159. Min Act: -0.1700
Data Index: 3499089 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.5221. Min Act: -0.1700
Data Index: 5643403 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.5534. Min Act: -0.1700
Data Index: 4064154 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.4909. Min Act: -0.1700
Data Index: 4064153 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.4909. Min Act: -0.1700
Data Index: 4044892 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.4596. Min Act: -0.1700
Data Index: 6747775 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.4284. Min Act: -0.1700
Data Index: 2201592 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.4284. Min Act: -0.1700
Data Index: 990511 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.4284. Min Act: -0.1700
Data Index: 7351145 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3971. Min Act: -0.1700
Data Index: 3256435 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3971. Min Act: -0.1700
Data Index: 8287265 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3971. Min Act: -0.1700
Data Index: 8287266 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3659. Min Act: -0.1700
Data Index: 51576 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3659. Min Act: -0.1700
Data Index: 2838317 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3659. Min Act: -0.1700
Data Index: 8731664 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3659. Min Act: -0.1700
Data Index: 4369231 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3659. Min Act: -0.1700
Data Index: 4504095 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3346. Min Act: -0.1700
Data Index: 696603 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8346. Min Range: -5.8346
Max Act: 5.3346. Min Act: -0.1700
Data Index: 6024386 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19