Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.6221. Min Act: -0.1700
Data Index: 3366204 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.4346. Min Act: -0.1700
Data Index: 251319 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.3409. Min Act: -0.1700
Data Index: 150332 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.3096. Min Act: -0.1700
Data Index: 477507 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.2784. Min Act: -0.1700
Data Index: 4111824 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.2159. Min Act: -0.1700
Data Index: 3716717 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.2159. Min Act: -0.1700
Data Index: 2680461 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1846. Min Act: -0.1700
Data Index: 535513 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1846. Min Act: -0.1700
Data Index: 2205211 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1533. Min Act: -0.1700
Data Index: 4412058 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1533. Min Act: -0.1700
Data Index: 5622938 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1221. Min Act: -0.1700
Data Index: 1068640 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1533. Min Act: -0.1700
Data Index: 6609221 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1221. Min Act: -0.1700
Data Index: 5445577 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1221. Min Act: -0.1700
Data Index: 188936 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.1221. Min Act: -0.1700
Data Index: 392329 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.0596. Min Act: -0.1700
Data Index: 5085771 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.0908. Min Act: -0.1700
Data Index: 761352 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.0908. Min Act: -0.1700
Data Index: 4297862 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6221. Min Range: -4.6221
Max Act: 4.0908. Min Act: -0.1700
Data Index: 432603 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19