Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.2310. Min Act: -0.1700
Data Index: 8200715 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.1685. Min Act: -0.1700
Data Index: 7966388 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.1373. Min Act: -0.1700
Data Index: 2939126 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.1060. Min Act: -0.1700
Data Index: 2016630 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.1060. Min Act: -0.1700
Data Index: 6160592 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.0748. Min Act: -0.1700
Data Index: 5157771 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.0435. Min Act: -0.1700
Data Index: 7564281 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.0123. Min Act: -0.1700
Data Index: 4437821 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.0123. Min Act: -0.1700
Data Index: 1162879 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9810. Min Act: -0.1700
Data Index: 5361572 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9810. Min Act: -0.1700
Data Index: 1130158 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2310. Min Range: -5.2310
Max Act: 5.0123. Min Act: -0.1700
Data Index: 3401077 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9498. Min Act: -0.1700
Data Index: 6460470 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9498. Min Act: -0.1700
Data Index: 3810759 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9498. Min Act: -0.1700
Data Index: 5890518 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9498. Min Act: -0.1700
Data Index: 516283 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9810. Min Act: -0.1700
Data Index: 7692301 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9185. Min Act: -0.1700
Data Index: 1588362 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9185. Min Act: -0.1700
Data Index: 367901 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2310. Min Range: -5.2310
Max Act: 4.9498. Min Act: -0.1700
Data Index: 5730765 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19