Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.3066. Min Act: -0.1700
Data Index: 444462 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.2537. Min Act: -0.1700
Data Index: 5833390 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.2009. Min Act: -0.1486
Data Index: 7552281 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.1481. Min Act: -0.1672
Data Index: 3129571 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.1305. Min Act: -0.1689
Data Index: 1673976 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0955. Min Act: -0.1700
Data Index: 7951485 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0955. Min Act: -0.1700
Data Index: 1584782 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0955. Min Act: -0.1700
Data Index: 5321855 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0605. Min Act: -0.1700
Data Index: 6695358 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0605. Min Act: -0.1659
Data Index: 3270569 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0605. Min Act: -0.1677
Data Index: 4503150 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0780. Min Act: -0.1677
Data Index: 72026 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0430. Min Act: -0.1696
Data Index: 7135770 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0430. Min Act: -0.1691
Data Index: 4496519 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0256. Min Act: -0.1700
Data Index: 7041194 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0256. Min Act: -0.1699
Data Index: 7387060 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0256. Min Act: -0.1682
Data Index: 8187036 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0256. Min Act: -0.1700
Data Index: 8333514 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0256. Min Act: -0.1691
Data Index: 737101 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3066. Min Range: -1.3066
Max Act: 1.0082. Min Act: -0.1700
Data Index: 5003358 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19