Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.9205. Min Act: -0.1700
Data Index: 5931117 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.7955. Min Act: -0.1700
Data Index: 3156176 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.6080. Min Act: -0.1700
Data Index: 7700567 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.4830. Min Act: -0.1700
Data Index: 6884268 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.3580. Min Act: -0.1700
Data Index: 7911290 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.2955. Min Act: -0.1700
Data Index: 7224571 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.2955. Min Act: -0.1700
Data Index: 7558924 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9205. Min Range: -11.9205
Max Act: 11.1080. Min Act: -0.1700
Data Index: 2055164 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9830. Min Act: -0.1700
Data Index: 8563764 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9830. Min Act: -0.1700
Data Index: 8751909 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9830. Min Act: -0.1700
Data Index: 710431 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9830. Min Act: -0.1700
Data Index: 1275409 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9205. Min Act: -0.1700
Data Index: 4224401 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9205. Min Act: -0.1700
Data Index: 7609573 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9205. Min Act: -0.1700
Data Index: 3804836 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9205. Min Act: -0.1700
Data Index: 2045574 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9205. Min Act: -0.1700
Data Index: 1249224 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.9205. Min Act: -0.1700
Data Index: 4994701 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.8580. Min Act: -0.1700
Data Index: 2515495 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9205. Min Range: -11.9205
Max Act: 10.8580. Min Act: -0.1700
Data Index: 92740 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19