Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4760 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.7321. Min Act: -0.1700
Data Index: 3163273 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.6520. Min Act: -0.1700
Data Index: 5533018 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.6038. Min Act: -0.1700
Data Index: 7012375 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5877. Min Act: -0.1700
Data Index: 7586604 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5716. Min Act: -0.1700
Data Index: 7012363 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5877. Min Act: -0.1700
Data Index: 5556390 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5877. Min Act: -0.1700
Data Index: 7736555 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5716. Min Act: -0.1700
Data Index: 7677756 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5393. Min Act: -0.1700
Data Index: 5718449 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5232. Min Act: -0.1700
Data Index: 6744015 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5232. Min Act: -0.1700
Data Index: 792278 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5070. Min Act: -0.1700
Data Index: 4939351 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5070. Min Act: -0.1700
Data Index: 1493398 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.5070. Min Act: -0.1700
Data Index: 7012361 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.4908. Min Act: -0.1700
Data Index: 7012377 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.4746. Min Act: -0.1700
Data Index: 8644424 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.4583. Min Act: -0.1700
Data Index: 3895543 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.4583. Min Act: -0.1700
Data Index: 485638 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.4583. Min Act: -0.1700
Data Index: 7883242 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7321. Min Range: -2.7321
Max Act: 2.4421. Min Act: -0.1700
Data Index: 885095 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19