Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0238. Min Range: -7.0238
Max Act: 7.0238. Min Act: -0.1700
Data Index: 6506173 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.9613. Min Act: -0.1700
Data Index: 8158198 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.9300. Min Act: -0.1700
Data Index: 6267805 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.9300. Min Act: -0.1700
Data Index: 2281073 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.8675. Min Act: -0.1700
Data Index: 5100143 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.8363. Min Act: -0.1700
Data Index: 5981906 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.8363. Min Act: -0.1700
Data Index: 6029129 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.8050. Min Act: -0.1700
Data Index: 4605793 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7738. Min Act: -0.1700
Data Index: 7580854 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7738. Min Act: -0.1700
Data Index: 2530830 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7738. Min Act: -0.1700
Data Index: 2951592 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7738. Min Act: -0.1700
Data Index: 7436718 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7425. Min Act: -0.1700
Data Index: 1941785 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7425. Min Act: -0.1700
Data Index: 725736 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7425. Min Act: -0.1700
Data Index: 8295240 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7113. Min Act: -0.1700
Data Index: 2956894 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7113. Min Act: -0.1700
Data Index: 899820 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.6488. Min Act: -0.1700
Data Index: 2251069 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.7113. Min Act: -0.1700
Data Index: 3902379 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0238. Min Range: -7.0238
Max Act: 6.6800. Min Act: -0.1700
Data Index: 5832809 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19