Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.6832. Min Act: -0.1700
Data Index: 10210 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.6207. Min Act: -0.1700
Data Index: 4803678 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.5895. Min Act: -0.1700
Data Index: 7070351 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.5582. Min Act: -0.1700
Data Index: 7070352 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.4332. Min Act: -0.1700
Data Index: 778639 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.4020. Min Act: -0.1700
Data Index: 5417581 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.4020. Min Act: -0.1700
Data Index: 373856 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.4020. Min Act: -0.1700
Data Index: 5970898 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.3707. Min Act: -0.1700
Data Index: 7943293 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.3707. Min Act: -0.1700
Data Index: 2741837 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.3082. Min Act: -0.1700
Data Index: 4484371 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2145. Min Act: -0.1700
Data Index: 1276515 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2457. Min Act: -0.1700
Data Index: 8215628 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2145. Min Act: -0.1700
Data Index: 1069606 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2457. Min Act: -0.1700
Data Index: 8635527 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2770. Min Act: -0.1700
Data Index: 6862442 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2770. Min Act: -0.1700
Data Index: 5782221 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2145. Min Act: -0.1700
Data Index: 2270857 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.2145. Min Act: -0.1700
Data Index: 8258779 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6832. Min Range: -6.6832
Max Act: 6.1832. Min Act: -0.1700
Data Index: 4076296 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19