Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.8592. Min Act: -0.1700
Data Index: 7778230 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.8280. Min Act: -0.1700
Data Index: 2370356 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.8280. Min Act: -0.1700
Data Index: 4520253 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7967. Min Act: -0.1700
Data Index: 8115449 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7967. Min Act: -0.1700
Data Index: 2179776 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7654. Min Act: -0.1700
Data Index: 8498827 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7967. Min Act: -0.1700
Data Index: 2221652 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7341. Min Act: -0.1700
Data Index: 314617 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7341. Min Act: -0.1700
Data Index: 667739 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7185. Min Act: -0.1700
Data Index: 4241223 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.7341. Min Act: -0.1700
Data Index: 611714 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6872. Min Act: -0.1700
Data Index: 3357601 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6872. Min Act: -0.1700
Data Index: 8033934 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6872. Min Act: -0.1700
Data Index: 1205395 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6716. Min Act: -0.1700
Data Index: 5015328 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6559. Min Act: -0.1700
Data Index: 2228478 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6559. Min Act: -0.1700
Data Index: 2493566 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6559. Min Act: -0.1700
Data Index: 2839002 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6559. Min Act: -0.1700
Data Index: 1091473 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8592. Min Range: -3.8592
Max Act: 3.6716. Min Act: -0.1700
Data Index: 7018542 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19