Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.8711. Min Act: -0.1700
Data Index: 262053 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.7774. Min Act: -0.1700
Data Index: 6982920 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.7149. Min Act: -0.1700
Data Index: 5140482 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.6524. Min Act: -0.1700
Data Index: 2021603 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.6524. Min Act: -0.1700
Data Index: 5570858 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.6211. Min Act: -0.1700
Data Index: 5490773 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.5899. Min Act: -0.1700
Data Index: 6009358 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.5274. Min Act: -0.1700
Data Index: 7092406 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4961. Min Act: -0.1700
Data Index: 405163 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4961. Min Act: -0.1700
Data Index: 5566489 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4649. Min Act: -0.1700
Data Index: 2513363 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4961. Min Act: -0.1700
Data Index: 4584886 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4649. Min Act: -0.1700
Data Index: 1764780 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4649. Min Act: -0.1700
Data Index: 4400282 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4336. Min Act: -0.1700
Data Index: 4918213 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4024. Min Act: -0.1700
Data Index: 527489 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4336. Min Act: -0.1700
Data Index: 1397562 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4336. Min Act: -0.1700
Data Index: 4166807 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4336. Min Act: -0.1700
Data Index: 7065469 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8711. Min Range: -5.8711
Max Act: 5.4336. Min Act: -0.1700
Data Index: 5234986 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19