Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.7138. Min Act: -0.1700
Data Index: 839039 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.5888. Min Act: -0.1700
Data Index: 7023380 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.4951. Min Act: -0.1700
Data Index: 8569702 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2763. Min Act: -0.1700
Data Index: 2881387 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2763. Min Act: -0.1700
Data Index: 8568574 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.2138. Min Act: -0.1700
Data Index: 4523602 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1826. Min Act: -0.1700
Data Index: 4611132 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1826. Min Act: -0.1700
Data Index: 6126896 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1513. Min Act: -0.1700
Data Index: 7428418 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1513. Min Act: -0.1700
Data Index: 2018769 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1201. Min Act: -0.1700
Data Index: 4609029 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1201. Min Act: -0.1700
Data Index: 494146 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.1201. Min Act: -0.1700
Data Index: 4257019 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0888. Min Act: -0.1700
Data Index: 1131448 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0576. Min Act: -0.1700
Data Index: 1894909 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0888. Min Act: -0.1700
Data Index: 266014 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0888. Min Act: -0.1700
Data Index: 7528492 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0888. Min Act: -0.1700
Data Index: 7971236 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0888. Min Act: -0.1700
Data Index: 1895368 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7138. Min Range: -7.7138
Max Act: 7.0888. Min Act: -0.1700
Data Index: 2299774 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19