Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.2929. Min Act: -0.1700
Data Index: 592651 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.2929. Min Act: -0.1700
Data Index: 3560742 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.2617. Min Act: -0.1700
Data Index: 3560704 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1679. Min Act: -0.1700
Data Index: 3815035 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1679. Min Act: -0.1700
Data Index: 3570975 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1679. Min Act: -0.1700
Data Index: 7366949 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1367. Min Act: -0.1700
Data Index: 4488165 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1054. Min Act: -0.1700
Data Index: 6812964 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1054. Min Act: -0.1700
Data Index: 5597118 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1054. Min Act: -0.1700
Data Index: 3930262 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1054. Min Act: -0.1700
Data Index: 7419876 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1054. Min Act: -0.1700
Data Index: 7757919 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0741. Min Act: -0.1700
Data Index: 3273688 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0741. Min Act: -0.1700
Data Index: 6374634 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0429. Min Act: -0.1700
Data Index: 7005990 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0429. Min Act: -0.1700
Data Index: 6234367 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0429. Min Act: -0.1700
Data Index: 4314351 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0429. Min Act: -0.1700
Data Index: 2999129 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0429. Min Act: -0.1700
Data Index: 7937119 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0116. Min Act: -0.1700
Data Index: 5507567 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19