Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 641 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.4538. Min Act: -0.1700
Data Index: 6874557 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.1413. Min Act: -0.1700
Data Index: 8487076 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.1101. Min Act: -0.1700
Data Index: 5720932 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.0476. Min Act: -0.1700
Data Index: 2860575 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9851. Min Act: -0.1700
Data Index: 8022845 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.8601. Min Act: -0.1700
Data Index: 3962801 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.8601. Min Act: -0.1700
Data Index: 5559334 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4914336 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.7976. Min Act: -0.1700
Data Index: 4298845 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.7976. Min Act: -0.1700
Data Index: 2768278 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.7663. Min Act: -0.1700
Data Index: 404186 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.7038. Min Act: -0.1700
Data Index: 7582307 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4538. Min Range: -6.4538
Max Act: 4.9851. Min Act: -0.1700
Data Index: 2350456 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.6726. Min Act: -0.1700
Data Index: 8267118 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.6413. Min Act: -0.1700
Data Index: 1065313 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.6101. Min Act: -0.1700
Data Index: 6272669 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.6101. Min Act: -0.1700
Data Index: 5404493 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.6413. Min Act: -0.1700
Data Index: 7185052 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.6101. Min Act: -0.1700
Data Index: 1240780 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.6726. Min Act: -0.1700
Data Index: 7272674 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19