Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7451. Min Range: -6.7451
Max Act: 6.7451. Min Act: -0.1700
Data Index: 1890555 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7451. Min Range: -6.7451
Max Act: 6.5264. Min Act: -0.1700
Data Index: 1890562 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7451. Min Range: -6.7451
Max Act: 6.3389. Min Act: -0.1700
Data Index: 8207365 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7451. Min Range: -6.7451
Max Act: 6.2451. Min Act: -0.1700
Data Index: 4865744 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7451. Min Range: -6.7451
Max Act: 6.1514. Min Act: -0.1700
Data Index: 8363000 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7451. Min Range: -6.7451
Max Act: 6.0576. Min Act: -0.1700
Data Index: 5834306 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.9951. Min Act: -0.1700
Data Index: 3675079 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.9639. Min Act: -0.1700
Data Index: 2062386 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.9326. Min Act: -0.1700
Data Index: 7020459 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.9014. Min Act: -0.1700
Data Index: 732109 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 7357505 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.9014. Min Act: -0.1700
Data Index: 283478 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.9014. Min Act: -0.1700
Data Index: 1261470 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 2019709 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8389. Min Act: -0.1700
Data Index: 4942698 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 1220131 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 1662250 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8389. Min Act: -0.1700
Data Index: 7420026 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 4886777 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7451. Min Range: -6.7451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 2729388 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19