Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.7423. Min Act: -0.1700
Data Index: 7270464 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.7111. Min Act: -0.1700
Data Index: 6755269 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6798. Min Act: -0.1700
Data Index: 8671508 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6486. Min Act: -0.1700
Data Index: 2173067 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6798. Min Act: -0.1700
Data Index: 2064057 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6486. Min Act: -0.1700
Data Index: 3281334 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5861. Min Act: -0.1700
Data Index: 8682624 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6173. Min Act: -0.1700
Data Index: 6675026 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5861. Min Act: -0.1700
Data Index: 1631342 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5861. Min Act: -0.1700
Data Index: 4822496 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5548. Min Act: -0.1700
Data Index: 1857396 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5548. Min Act: -0.1700
Data Index: 606339 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.4923. Min Act: -0.1700
Data Index: 989134 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.4610. Min Act: -0.1700
Data Index: 836025 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.4610. Min Act: -0.1700
Data Index: 3557760 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.4923. Min Act: -0.1700
Data Index: 6159790 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5236. Min Act: -0.1700
Data Index: 5384282 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.4923. Min Act: -0.1700
Data Index: 2136746 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.4610. Min Act: -0.1700
Data Index: 3812229 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.4610. Min Act: -0.1700
Data Index: 5312485 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19