Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0102. Min Range: -10.0102
Max Act: 10.0102. Min Act: -0.1700
Data Index: 108123 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.8227. Min Act: -0.1700
Data Index: 5099395 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.7602. Min Act: -0.1700
Data Index: 3299270 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.6977. Min Act: -0.1700
Data Index: 863919 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.6977. Min Act: -0.1700
Data Index: 2609030 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.6977. Min Act: -0.1700
Data Index: 4463136 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.6352. Min Act: -0.1700
Data Index: 7710753 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.5727. Min Act: -0.1700
Data Index: 2353673 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.5102. Min Act: -0.1700
Data Index: 7230896 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.5727. Min Act: -0.1700
Data Index: 184783 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.5727. Min Act: -0.1700
Data Index: 8082629 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.5102. Min Act: -0.1700
Data Index: 4769760 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.4477. Min Act: -0.1700
Data Index: 7151349 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.4477. Min Act: -0.1700
Data Index: 2030784 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.4477. Min Act: -0.1700
Data Index: 1143559 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.4477. Min Act: -0.1700
Data Index: 2172784 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.4477. Min Act: -0.1700
Data Index: 445203 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.4477. Min Act: -0.1700
Data Index: 6238238 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.3852. Min Act: -0.1700
Data Index: 7201111 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0102. Min Range: -10.0102
Max Act: 9.3852. Min Act: -0.1700
Data Index: 4431287 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19