Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.8548. Min Act: -0.1700
Data Index: 5583595 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.8078. Min Act: -0.1700
Data Index: 8340936 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.5419. Min Act: -0.1700
Data Index: 985022 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.5262. Min Act: -0.1700
Data Index: 3199875 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.5262. Min Act: -0.1700
Data Index: 5747534 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4949. Min Act: -0.1700
Data Index: 8207384 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.5106. Min Act: -0.1700
Data Index: 5569357 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4479. Min Act: -0.1700
Data Index: 3434338 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4636. Min Act: -0.1700
Data Index: 4542492 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4479. Min Act: -0.1700
Data Index: 5410226 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4165. Min Act: -0.1700
Data Index: 5569358 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4322. Min Act: -0.1700
Data Index: 6439971 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4322. Min Act: -0.1700
Data Index: 5098986 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.4165. Min Act: -0.1700
Data Index: 4562921 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.3695. Min Act: -0.1700
Data Index: 5477647 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.3695. Min Act: -0.1700
Data Index: 8553684 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.3695. Min Act: -0.1700
Data Index: 4155461 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.3381. Min Act: -0.1700
Data Index: 472698 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.3067. Min Act: -0.1700
Data Index: 8011432 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8548. Min Range: -3.8548
Max Act: 3.3067. Min Act: -0.1700
Data Index: 4155462 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19