Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6354 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3067. Min Range: -8.3067
Max Act: 8.3067. Min Act: -0.1700
Data Index: 1420171 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.7754. Min Act: -0.1700
Data Index: 8592789 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.6192. Min Act: -0.1700
Data Index: 2485510 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.5879. Min Act: -0.1700
Data Index: 3145210 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.5879. Min Act: -0.1700
Data Index: 8667913 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.5254. Min Act: -0.1700
Data Index: 2473623 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.5254. Min Act: -0.1700
Data Index: 1558420 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4942. Min Act: -0.1700
Data Index: 6680594 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4942. Min Act: -0.1700
Data Index: 8361558 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4629. Min Act: -0.1700
Data Index: 6934694 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4004. Min Act: -0.1700
Data Index: 5371414 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4004. Min Act: -0.1700
Data Index: 6455378 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4004. Min Act: -0.1700
Data Index: 8452832 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4004. Min Act: -0.1700
Data Index: 6523565 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.4004. Min Act: -0.1700
Data Index: 8593205 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.3692. Min Act: -0.1700
Data Index: 8667909 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.3692. Min Act: -0.1700
Data Index: 6924650 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.3692. Min Act: -0.1700
Data Index: 8569279 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.3692. Min Act: -0.1700
Data Index: 5882833 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3067. Min Range: -8.3067
Max Act: 7.3692. Min Act: -0.1700
Data Index: 2619809 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19