Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.6277. Min Act: -0.1700
Data Index: 7572186 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.4402. Min Act: -0.1700
Data Index: 216350 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.3152. Min Act: -0.1700
Data Index: 629557 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.3152. Min Act: -0.1700
Data Index: 216351 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.3152. Min Act: -0.1700
Data Index: 7893403 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.2839. Min Act: -0.1700
Data Index: 8323178 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.2839. Min Act: -0.1700
Data Index: 755984 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.2527. Min Act: -0.1700
Data Index: 4748581 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.2527. Min Act: -0.1700
Data Index: 6721425 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.2214. Min Act: -0.1700
Data Index: 4212918 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.2214. Min Act: -0.1700
Data Index: 6059476 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.1902. Min Act: -0.1700
Data Index: 7392121 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.2214. Min Act: -0.1700
Data Index: 7230162 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.1902. Min Act: -0.1700
Data Index: 4328937 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.1277. Min Act: -0.1700
Data Index: 1440320 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.1589. Min Act: -0.1700
Data Index: 5743635 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.0964. Min Act: -0.1700
Data Index: 8023279 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.0651. Min Act: -0.1700
Data Index: 4320639 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.0651. Min Act: -0.1700
Data Index: 1968845 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6277. Min Range: -4.6277
Max Act: 4.0339. Min Act: -0.1700
Data Index: 4719714 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19