Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.5782. Min Act: -0.1700
Data Index: 7872509 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.4531. Min Act: -0.1700
Data Index: 1101478 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.4219. Min Act: -0.1700
Data Index: 1541026 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.4219. Min Act: -0.1700
Data Index: 6914036 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.3906. Min Act: -0.1700
Data Index: 5095730 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.3906. Min Act: -0.1700
Data Index: 7872510 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.3594. Min Act: -0.1700
Data Index: 2557099 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.3594. Min Act: -0.1700
Data Index: 5126597 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2969. Min Act: -0.1700
Data Index: 3804692 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.3281. Min Act: -0.1700
Data Index: 4370265 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.3281. Min Act: -0.1700
Data Index: 1302237 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2969. Min Act: -0.1700
Data Index: 6645505 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2656. Min Act: -0.1700
Data Index: 6886622 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2656. Min Act: -0.1700
Data Index: 7713265 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2656. Min Act: -0.1700
Data Index: 6652784 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2344. Min Act: -0.1700
Data Index: 3133571 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2344. Min Act: -0.1700
Data Index: 7138051 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2344. Min Act: -0.1700
Data Index: 7762910 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2344. Min Act: -0.1700
Data Index: 768379 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5782. Min Range: -4.5782
Max Act: 4.2344. Min Act: -0.1700
Data Index: 1886870 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19