Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5851 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.4781. Min Act: -0.1700
Data Index: 535408 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.4156. Min Act: -0.1700
Data Index: 5413803 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.4156. Min Act: -0.1700
Data Index: 912600 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.2281. Min Act: -0.1700
Data Index: 1590582 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.2281. Min Act: -0.1700
Data Index: 1223263 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.1656. Min Act: -0.1700
Data Index: 5555135 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.1656. Min Act: -0.1700
Data Index: 8463543 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.0406. Min Act: -0.1700
Data Index: 3037951 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.0406. Min Act: -0.1700
Data Index: 7445836 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.0406. Min Act: -0.1700
Data Index: 6751534 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.0406. Min Act: -0.1700
Data Index: 3583133 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.0406. Min Act: -0.1700
Data Index: 6344445 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4781. Min Range: -10.4781
Max Act: 9.9781. Min Act: -0.1700
Data Index: 504309 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4781. Min Range: -10.4781
Max Act: 10.0406. Min Act: -0.1700
Data Index: 1710119 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4781. Min Range: -10.4781
Max Act: 9.9156. Min Act: -0.1700
Data Index: 4975691 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4781. Min Range: -10.4781
Max Act: 9.9781. Min Act: -0.1700
Data Index: 6027942 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4781. Min Range: -10.4781
Max Act: 9.9781. Min Act: -0.1700
Data Index: 5979919 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4781. Min Range: -10.4781
Max Act: 9.9781. Min Act: -0.1700
Data Index: 5597882 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4781. Min Range: -10.4781
Max Act: 9.9156. Min Act: -0.1700
Data Index: 4542297 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4781. Min Range: -10.4781
Max Act: 9.9156. Min Act: -0.1700
Data Index: 1122017 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19