Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5266 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.7306. Min Act: -0.1700
Data Index: 2505626 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.3868. Min Act: -0.1700
Data Index: 4535138 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.1993. Min Act: -0.1700
Data Index: 5267217 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.1993. Min Act: -0.1700
Data Index: 7293921 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.1681. Min Act: -0.1700
Data Index: 6642318 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.1368. Min Act: -0.1700
Data Index: 7871940 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.0743. Min Act: -0.1700
Data Index: 6385508 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.0431. Min Act: -0.1700
Data Index: 5698007 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.0431. Min Act: -0.1700
Data Index: 6526199 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.0118. Min Act: -0.1700
Data Index: 4742682 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.0118. Min Act: -0.1700
Data Index: 1972686 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7306. Min Range: -6.7306
Max Act: 6.0118. Min Act: -0.1700
Data Index: 4055666 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.9806. Min Act: -0.1700
Data Index: 7998516 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.9806. Min Act: -0.1700
Data Index: 4412045 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.9806. Min Act: -0.1700
Data Index: 6385510 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.9806. Min Act: -0.1700
Data Index: 7691690 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.9493. Min Act: -0.1700
Data Index: 6288156 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.9493. Min Act: -0.1700
Data Index: 6526198 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.9181. Min Act: -0.1700
Data Index: 4215887 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7306. Min Range: -6.7306
Max Act: 5.8868. Min Act: -0.1700
Data Index: 5971356 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19