Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.3723. Min Act: -0.1700
Data Index: 1351133 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.3252. Min Act: -0.1700
Data Index: 3055330 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.3252. Min Act: -0.1700
Data Index: 2874945 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.3252. Min Act: -0.1700
Data Index: 882365 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.3252. Min Act: -0.1700
Data Index: 2717235 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.3252. Min Act: -0.1700
Data Index: 6532899 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2938. Min Act: -0.1700
Data Index: 4163997 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2938. Min Act: -0.1700
Data Index: 142596 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2938. Min Act: -0.1700
Data Index: 4827563 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2781. Min Act: -0.1700
Data Index: 6928750 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2781. Min Act: -0.1700
Data Index: 3992664 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2781. Min Act: -0.1700
Data Index: 605624 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2781. Min Act: -0.1700
Data Index: 8802109 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2624. Min Act: -0.1700
Data Index: 6116970 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2624. Min Act: -0.1700
Data Index: 7943927 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2781. Min Act: -0.1700
Data Index: 6016583 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2624. Min Act: -0.1700
Data Index: 6452416 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2310. Min Act: -0.1700
Data Index: 8216406 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2467. Min Act: -0.1700
Data Index: 1087621 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3723. Min Range: -3.3723
Max Act: 3.2310. Min Act: -0.1700
Data Index: 7495926 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19