Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 324 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3205. Min Range: -8.3205
Max Act: 8.3205. Min Act: -0.1700
Data Index: 6552721 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3205. Min Range: -8.3205
Max Act: 8.0705. Min Act: -0.1700
Data Index: 5556083 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3205. Min Range: -8.3205
Max Act: 8.0393. Min Act: -0.1700
Data Index: 8754267 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.9768. Min Act: -0.1700
Data Index: 5858415 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.7893. Min Act: -0.1700
Data Index: 4995418 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.7893. Min Act: -0.1700
Data Index: 1429220 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.7893. Min Act: -0.1700
Data Index: 1147643 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.6955. Min Act: -0.1700
Data Index: 3203793 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.6643. Min Act: -0.1700
Data Index: 7707086 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.6643. Min Act: -0.1700
Data Index: 4673160 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.6955. Min Act: -0.1700
Data Index: 2338946 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.5393. Min Act: -0.1700
Data Index: 749030 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.5705. Min Act: -0.1700
Data Index: 3426680 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.5705. Min Act: -0.1700
Data Index: 5000881 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.5080. Min Act: -0.1700
Data Index: 7825388 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.5080. Min Act: -0.1700
Data Index: 192064 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.4768. Min Act: -0.1700
Data Index: 4558423 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.4768. Min Act: -0.1700
Data Index: 4349829 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.4768. Min Act: -0.1700
Data Index: 4004222 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3205. Min Range: -8.3205
Max Act: 7.4768. Min Act: -0.1700
Data Index: 6150658 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19