Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4760 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.7257. Min Act: -0.1700
Data Index: 7257870 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.7257. Min Act: -0.1700
Data Index: 2121522 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.5694. Min Act: -0.1700
Data Index: 2881615 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.5382. Min Act: -0.1700
Data Index: 2486788 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4444. Min Act: -0.1700
Data Index: 175371 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4444. Min Act: -0.1700
Data Index: 5387499 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4444. Min Act: -0.1700
Data Index: 4552702 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4444. Min Act: -0.1700
Data Index: 5150855 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4132. Min Act: -0.1700
Data Index: 4989311 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4132. Min Act: -0.1700
Data Index: 3758851 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4132. Min Act: -0.1700
Data Index: 3374667 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.4132. Min Act: -0.1700
Data Index: 773097 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.3819. Min Act: -0.1700
Data Index: 3933950 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.3507. Min Act: -0.1700
Data Index: 7426536 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.3507. Min Act: -0.1700
Data Index: 5471349 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.3194. Min Act: -0.1700
Data Index: 6438909 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.2882. Min Act: -0.1700
Data Index: 4073687 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.2882. Min Act: -0.1700
Data Index: 7524172 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.3194. Min Act: -0.1700
Data Index: 4102225 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7257. Min Range: -5.7257
Max Act: 5.3194. Min Act: -0.1700
Data Index: 6455594 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19