Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.7341. Min Act: -0.1700
Data Index: 2793797 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.6091. Min Act: -0.1700
Data Index: 1043251 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.6091. Min Act: -0.1700
Data Index: 2847981 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.5778. Min Act: -0.1700
Data Index: 1027332 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.5466. Min Act: -0.1700
Data Index: 6426372 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.4841. Min Act: -0.1700
Data Index: 1031977 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.5153. Min Act: -0.1700
Data Index: 7211388 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.4528. Min Act: -0.1700
Data Index: 2793798 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.4216. Min Act: -0.1700
Data Index: 2793799 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.4216. Min Act: -0.1700
Data Index: 1493473 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3903. Min Act: -0.1700
Data Index: 6261450 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3591. Min Act: -0.1700
Data Index: 23790 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3903. Min Act: -0.1700
Data Index: 7837577 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3591. Min Act: -0.1700
Data Index: 3642278 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3591. Min Act: -0.1700
Data Index: 2125344 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3278. Min Act: -0.1700
Data Index: 5845368 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3278. Min Act: -0.1700
Data Index: 2793794 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3278. Min Act: -0.1700
Data Index: 4601837 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3278. Min Act: -0.1700
Data Index: 7211395 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7341. Min Range: -6.7341
Max Act: 6.3278. Min Act: -0.1700
Data Index: 606408 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19