Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 338 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4049. Min Act: -0.0001
Data Index: 815046 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4378. Min Act: -0.0001
Data Index: 1062835 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3632. Min Act: -0.0001
Data Index: 1257267 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3202. Min Act: -0.0001
Data Index: 1108356 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3340. Min Act: -0.0001
Data Index: 1285267 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3401. Min Act: -0.0001
Data Index: 1030452 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3536. Min Act: -0.0000
Data Index: 561166 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3421. Min Act: -0.0000
Data Index: 622907 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3156. Min Act: -0.0001
Data Index: 82687 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.2884. Min Act: -0.0000
Data Index: 1127697 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3117. Min Act: -0.0001
Data Index: 1081331 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3236. Min Act: -0.0001
Data Index: 50396 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3304. Min Act: -0.0001
Data Index: 1253505 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3363. Min Act: -0.0001
Data Index: 374316 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3238. Min Act: -0.0001
Data Index: 1203035 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.2861. Min Act: -0.0001
Data Index: 67073 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3434. Min Act: -0.0000
Data Index: 136825 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3277. Min Act: -0.0001
Data Index: 752338 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3015. Min Act: -0.0001
Data Index: 928188 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3024. Min Act: -0.0001
Data Index: 337290 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19