Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3331 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.3458. Min Act: -0.1700
Data Index: 1711801 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.3146. Min Act: -0.1700
Data Index: 8749796 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.2521. Min Act: -0.1700
Data Index: 100295 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1896. Min Act: -0.1700
Data Index: 8454250 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1271. Min Act: -0.1700
Data Index: 2804264 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1583. Min Act: -0.1700
Data Index: 6352219 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1583. Min Act: -0.1700
Data Index: 2283406 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1271. Min Act: -0.1700
Data Index: 8781924 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1271. Min Act: -0.1700
Data Index: 1785459 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1271. Min Act: -0.1700
Data Index: 7472156 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.1271. Min Act: -0.1700
Data Index: 1592551 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0958. Min Act: -0.1700
Data Index: 3574561 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0958. Min Act: -0.1700
Data Index: 7836285 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0802. Min Act: -0.1700
Data Index: 4889212 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0333. Min Act: -0.1700
Data Index: 6732212 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0020. Min Act: -0.1700
Data Index: 5932500 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0333. Min Act: -0.1700
Data Index: 4722350 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0020. Min Act: -0.1700
Data Index: 7948929 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3458. Min Range: -4.3458
Max Act: 3.9864. Min Act: -0.1700
Data Index: 1080522 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3458. Min Range: -4.3458
Max Act: 4.0020. Min Act: -0.1700
Data Index: 3713410 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19