Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5128 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.7915. Min Act: -0.1700
Data Index: 7162555 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6665. Min Act: -0.1699
Data Index: 1027478 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6665. Min Act: -0.1700
Data Index: 1980477 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6665. Min Act: -0.1700
Data Index: 2224527 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6352. Min Act: -0.1700
Data Index: 4814145 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6352. Min Act: -0.1700
Data Index: 3379639 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6040. Min Act: -0.1700
Data Index: 709241 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6040. Min Act: -0.1700
Data Index: 1050831 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 281765 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 6465204 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 4329233 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5415. Min Act: -0.1700
Data Index: 6183216 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 3393591 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5300241 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 1654957 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 7752776 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5415. Min Act: -0.1698
Data Index: 8443100 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 322701 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5727. Min Act: -0.1700
Data Index: 1439457 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7915. Min Range: -5.7915
Max Act: 5.5415. Min Act: -0.1700
Data Index: 4113234 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19