Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4055 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2561. Min Range: -7.2561
Max Act: 7.2561. Min Act: -0.1700
Data Index: 1447239 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2561. Min Range: -7.2561
Max Act: 7.1936. Min Act: -0.1700
Data Index: 3703439 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.6936. Min Act: -0.1699
Data Index: 5862660 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.6623. Min Act: -0.1700
Data Index: 2814877 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.5373. Min Act: -0.1696
Data Index: 2624942 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.5998. Min Act: -0.1697
Data Index: 7633729 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.5373. Min Act: -0.1700
Data Index: 8496908 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.4436. Min Act: -0.1700
Data Index: 7499198 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.4748. Min Act: -0.1700
Data Index: 2884590 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.3811. Min Act: -0.1700
Data Index: 5536531 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.3811. Min Act: -0.1700
Data Index: 718247 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.4436. Min Act: -0.1700
Data Index: 1509314 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.3811. Min Act: -0.1700
Data Index: 4446861 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.3186. Min Act: -0.1698
Data Index: 4253819 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.3186. Min Act: -0.1700
Data Index: 8722601 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.3498. Min Act: -0.1700
Data Index: 3811212 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.3186. Min Act: -0.1699
Data Index: 8548148 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.2561. Min Act: -0.1700
Data Index: 8408328 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.2561. Min Act: -0.1700
Data Index: 766260 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2561. Min Range: -7.2561
Max Act: 6.2248. Min Act: -0.1700
Data Index: 6473140 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19