Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3986. Min Act: -0.1700
Data Index: 6767529 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3986. Min Act: -0.1700
Data Index: 71444 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3674. Min Act: -0.1700
Data Index: 8800306 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3674. Min Act: -0.1700
Data Index: 3160262 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3674. Min Act: -0.1700
Data Index: 485250 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3674. Min Act: -0.1700
Data Index: 8212234 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3674. Min Act: -0.1700
Data Index: 3883382 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3674. Min Act: -0.1700
Data Index: 6793093 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3361. Min Act: -0.1700
Data Index: 562649 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3049. Min Act: -0.1700
Data Index: 8232614 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3049. Min Act: -0.1700
Data Index: 8410023 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3049. Min Act: -0.1700
Data Index: 2475834 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3049. Min Act: -0.1700
Data Index: 2044213 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3049. Min Act: -0.1700
Data Index: 1853996 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 1069865 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 7243320 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 4309562 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 132229 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 5434957 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 4960635 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19