Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.7638. Min Act: -0.1700
Data Index: 149252 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.5763. Min Act: -0.1700
Data Index: 3117629 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.5450. Min Act: -0.1700
Data Index: 5525815 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.4825. Min Act: -0.1700
Data Index: 7210844 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.4200. Min Act: -0.1700
Data Index: 2380612 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.4200. Min Act: -0.1700
Data Index: 3049090 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.3888. Min Act: -0.1700
Data Index: 6029691 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.3888. Min Act: -0.1700
Data Index: 5486989 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.3575. Min Act: -0.1700
Data Index: 1289045 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.3575. Min Act: -0.1700
Data Index: 906511 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.3263. Min Act: -0.1700
Data Index: 5587107 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.3263. Min Act: -0.1700
Data Index: 581488 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2950. Min Act: -0.1700
Data Index: 3990879 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2638. Min Act: -0.1700
Data Index: 305389 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2325. Min Act: -0.1700
Data Index: 3149101 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2325. Min Act: -0.1700
Data Index: 1005878 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2325. Min Act: -0.1700
Data Index: 4302096 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2325. Min Act: -0.1700
Data Index: 6705826 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2325. Min Act: -0.1700
Data Index: 5904273 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7638. Min Range: -6.7638
Max Act: 6.2325. Min Act: -0.1700
Data Index: 2009063 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19