Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.8897. Min Act: -0.1700
Data Index: 880767 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.6397. Min Act: -0.1699
Data Index: 7704493 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.6397. Min Act: -0.1700
Data Index: 6936061 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.6085. Min Act: -0.1700
Data Index: 1753443 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.6085. Min Act: -0.1700
Data Index: 4262180 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.5147. Min Act: -0.1700
Data Index: 1252497 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.4522. Min Act: -0.1700
Data Index: 8175749 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.4210. Min Act: -0.1700
Data Index: 7461728 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.3585. Min Act: -0.1700
Data Index: 6016012 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.3272. Min Act: -0.1700
Data Index: 6369807 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2647. Min Act: -0.1700
Data Index: 2504654 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.1710. Min Act: -0.1700
Data Index: 3950864 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.1710. Min Act: -0.1700
Data Index: 5780568 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.1085. Min Act: -0.1700
Data Index: 4795345 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.1085. Min Act: -0.1700
Data Index: 8190846 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 2683792 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 17210 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 2978742 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.0772. Min Act: -0.1700
Data Index: 7715409 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.0460. Min Act: -0.1700
Data Index: 2013490 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19