Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 962 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 740418 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 6672650 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.4192. Min Act: -0.1700
Data Index: 6924917 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3880. Min Act: -0.1700
Data Index: 2751775 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3567. Min Act: -0.1700
Data Index: 5047550 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2942. Min Act: -0.1700
Data Index: 1452954 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3567. Min Act: -0.1700
Data Index: 5968469 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3255. Min Act: -0.1700
Data Index: 3297034 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3255. Min Act: -0.1700
Data Index: 2850865 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3255. Min Act: -0.1700
Data Index: 1787160 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2942. Min Act: -0.1700
Data Index: 5779869 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2942. Min Act: -0.1700
Data Index: 3596196 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2942. Min Act: -0.1700
Data Index: 7345098 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2942. Min Act: -0.1700
Data Index: 8012803 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2942. Min Act: -0.1700
Data Index: 3597680 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 7010817 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 425662 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 714343 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 4571613 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2317. Min Act: -0.1700
Data Index: 230885 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19