Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5739 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.8472. Min Act: -0.1700
Data Index: 3271814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.7534. Min Act: -0.1700
Data Index: 1621699 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.6909. Min Act: -0.1700
Data Index: 4900051 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.6597. Min Act: -0.1700
Data Index: 5718872 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.6284. Min Act: -0.1656
Data Index: 127186 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.6284. Min Act: -0.1700
Data Index: 7085878 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5972. Min Act: -0.1686
Data Index: 2525565 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5972. Min Act: -0.1700
Data Index: 4722974 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5972. Min Act: -0.1690
Data Index: 8189730 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5659. Min Act: -0.1700
Data Index: 70116 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5659. Min Act: -0.1699
Data Index: 6492059 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5659. Min Act: -0.1700
Data Index: 2475416 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1700
Data Index: 975598 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1693
Data Index: 567819 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1700
Data Index: 1083275 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1700
Data Index: 274900 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1697
Data Index: 75503 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1695
Data Index: 81518 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1700
Data Index: 729476 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1699
Data Index: 748696 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19