Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1406. Min Range: -2.1406
Max Act: 2.1406. Min Act: -0.1700
Data Index: 1539715 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1406. Min Range: -2.1406
Max Act: 2.0063. Min Act: -0.1682
Data Index: 2397380 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1406. Min Range: -2.1406
Max Act: 2.0232. Min Act: -0.1698
Data Index: 8477727 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1406. Min Range: -2.1406
Max Act: 2.0232. Min Act: -0.1700
Data Index: 4816419 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.9385. Min Act: -0.1686
Data Index: 5957711 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.9215. Min Act: -0.1684
Data Index: 4724264 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.9045. Min Act: -0.1700
Data Index: 8434978 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.9045. Min Act: -0.1688
Data Index: 8510028 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.9385. Min Act: -0.1700
Data Index: 8592953 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.9045. Min Act: -0.1700
Data Index: 7758170 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8874. Min Act: -0.1700
Data Index: 4956934 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.9215. Min Act: -0.1690
Data Index: 2976374 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8703. Min Act: -0.1697
Data Index: 6531603 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8874. Min Act: -0.1700
Data Index: 7138874 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8703. Min Act: -0.1700
Data Index: 1825469 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8874. Min Act: -0.1700
Data Index: 4572693 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8874. Min Act: -0.1670
Data Index: 5013283 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8703. Min Act: -0.1698
Data Index: 7056416 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8703. Min Act: -0.1700
Data Index: 3167750 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1406. Min Range: -2.1406
Max Act: 1.8703. Min Act: -0.1700
Data Index: 7947356 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19