Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2147 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.2445. Min Act: -0.1700
Data Index: 6623832 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.2133. Min Act: -0.1700
Data Index: 2377469 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.1508. Min Act: -0.1700
Data Index: 7586358 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.1508. Min Act: -0.1692
Data Index: 1557090 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.1195. Min Act: -0.1673
Data Index: 5029271 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.1195. Min Act: -0.1699
Data Index: 6492707 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.1195. Min Act: -0.1699
Data Index: 6161524 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1641
Data Index: 8531244 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1700
Data Index: 2423382 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1694
Data Index: 2774918 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1699
Data Index: 186352 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1700
Data Index: 8264543 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1700
Data Index: 7928650 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1698
Data Index: 3995769 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0570. Min Act: -0.1677
Data Index: 3345706 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0570. Min Act: -0.1683
Data Index: 2296594 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0883. Min Act: -0.1700
Data Index: 3635718 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0570. Min Act: -0.1697
Data Index: 5031352 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0570. Min Act: -0.1700
Data Index: 6076361 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2445. Min Range: -6.2445
Max Act: 6.0570. Min Act: -0.1700
Data Index: 2297091 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19