Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 923 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.6286. Min Act: -0.1700
Data Index: 2968463 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.6286. Min Act: -0.1700
Data Index: 3012959 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.6286. Min Act: -0.1700
Data Index: 3510027 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5839922 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5775985 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5973. Min Act: -0.1700
Data Index: 7451072 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5973. Min Act: -0.1700
Data Index: 2968468 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 7451074 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 2801245 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5348. Min Act: -0.1698
Data Index: 5839919 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5348. Min Act: -0.1700
Data Index: 5755305 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 4508602 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 1051304 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 6458726 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 4468841 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 4212926 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 5839923 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5348. Min Act: -0.1700
Data Index: 2786798 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5348. Min Act: -0.1700
Data Index: 4552438 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5348. Min Act: -0.1700
Data Index: 716740 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19