Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5949 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7689. Min Act: -0.1700
Data Index: 6795626 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7376. Min Act: -0.1700
Data Index: 6310387 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7376. Min Act: -0.1700
Data Index: 322906 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7376. Min Act: -0.1700
Data Index: 459520 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7376. Min Act: -0.1700
Data Index: 358128 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7064. Min Act: -0.1700
Data Index: 2347767 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 1018933 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 204137 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 2350714 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 4616875 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 646820 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 8212946 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 7951583 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 6876676 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 6253551 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7220. Min Act: -0.1700
Data Index: 5317079 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7064. Min Act: -0.1700
Data Index: 1018931 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7064. Min Act: -0.1700
Data Index: 646822 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7064. Min Act: -0.1700
Data Index: 646824 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7689. Min Range: -3.7689
Max Act: 3.7064. Min Act: -0.1700
Data Index: 322908 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19