Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.9221. Min Act: -0.1700
Data Index: 5001816 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.6408. Min Act: -0.1700
Data Index: 6119825 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.5471. Min Act: -0.1700
Data Index: 4367132 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.4221. Min Act: -0.1700
Data Index: 7909669 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.2658. Min Act: -0.1700
Data Index: 2985316 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.2346. Min Act: -0.1700
Data Index: 1087776 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.2346. Min Act: -0.1700
Data Index: 4870870 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.2346. Min Act: -0.1700
Data Index: 3030000 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.2033. Min Act: -0.1700
Data Index: 2287425 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.2033. Min Act: -0.1700
Data Index: 7008656 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.2033. Min Act: -0.1700
Data Index: 5611908 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.1721. Min Act: -0.1700
Data Index: 640449 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.1721. Min Act: -0.1700
Data Index: 6119677 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.1721. Min Act: -0.1700
Data Index: 6254598 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.1408. Min Act: -0.1700
Data Index: 4677811 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.1096. Min Act: -0.1700
Data Index: 6343670 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.1408. Min Act: -0.1700
Data Index: 2766514 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.0783. Min Act: -0.1700
Data Index: 4085334 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.0471. Min Act: -0.1700
Data Index: 6133050 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9221. Min Range: -7.9221
Max Act: 7.0471. Min Act: -0.1700
Data Index: 6509304 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19