Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.5783. Min Act: -0.1700
Data Index: 4355821 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.5783. Min Act: -0.1700
Data Index: 1884933 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.3908. Min Act: -0.1700
Data Index: 2288302 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.3283. Min Act: -0.1700
Data Index: 2244933 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.2658. Min Act: -0.1700
Data Index: 1732611 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.2033. Min Act: -0.1700
Data Index: 4086407 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.2033. Min Act: -0.1700
Data Index: 1919086 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.1408. Min Act: -0.1700
Data Index: 7778242 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.1408. Min Act: -0.1700
Data Index: 3937319 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.1408. Min Act: -0.1700
Data Index: 2550718 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.1408. Min Act: -0.1700
Data Index: 1197424 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0783. Min Act: -0.1700
Data Index: 8435802 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0783. Min Act: -0.1700
Data Index: 5889610 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0158. Min Act: -0.1700
Data Index: 3120089 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0158. Min Act: -0.1700
Data Index: 4476470 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0158. Min Act: -0.1700
Data Index: 6548200 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0158. Min Act: -0.1700
Data Index: 2410399 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0158. Min Act: -0.1700
Data Index: 5925467 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0158. Min Act: -0.1700
Data Index: 2507994 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5783. Min Range: -9.5783
Max Act: 9.0158. Min Act: -0.1700
Data Index: 2618666 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19