Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5906 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.8234. Min Act: -0.1700
Data Index: 3355042 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.6984. Min Act: -0.1700
Data Index: 546459 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.6672. Min Act: -0.1700
Data Index: 3484976 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.6047. Min Act: -0.1700
Data Index: 5546714 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.6047. Min Act: -0.1700
Data Index: 6408252 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.5734. Min Act: -0.1700
Data Index: 2183843 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.5734. Min Act: -0.1700
Data Index: 5876626 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.5422. Min Act: -0.1700
Data Index: 312076 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.5109. Min Act: -0.1700
Data Index: 5104226 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.5422. Min Act: -0.1700
Data Index: 7743473 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.5109. Min Act: -0.1700
Data Index: 922326 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4797. Min Act: -0.1700
Data Index: 7610108 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4797. Min Act: -0.1700
Data Index: 5925973 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4484. Min Act: -0.1700
Data Index: 1563133 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4797. Min Act: -0.1700
Data Index: 7857566 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4172. Min Act: -0.1700
Data Index: 1402621 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4172. Min Act: -0.1700
Data Index: 1146548 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4172. Min Act: -0.1700
Data Index: 3973694 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4172. Min Act: -0.1700
Data Index: 575533 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4172. Min Act: -0.1700
Data Index: 2660689 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19