Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2590 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.5240. Min Act: -0.0001
Data Index: 476884 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.3057. Min Act: -0.0001
Data Index: 648781 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.5431. Min Act: -0.0001
Data Index: 1243926 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.1956. Min Act: -0.0001
Data Index: 259678 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.1726. Min Act: -0.0001
Data Index: 1354620 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.0554. Min Act: -0.0001
Data Index: 1285992 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.0228. Min Act: -0.0001
Data Index: 846228 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.0120. Min Act: -0.0001
Data Index: 422421 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.1877. Min Act: -0.0001
Data Index: 1116327 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.8529. Min Act: -0.0001
Data Index: 541984 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.9462. Min Act: -0.0001
Data Index: 1159899 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.9575. Min Act: -0.0001
Data Index: 965187 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5431. Min Range: -2.5431
Max Act: 2.1584. Min Act: -0.0001
Data Index: 159940 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.8680. Min Act: -0.0001
Data Index: 103153 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.9694. Min Act: -0.0001
Data Index: 148858 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.7926. Min Act: -0.0001
Data Index: 23393 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.8585. Min Act: -0.0001
Data Index: 336202 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.8390. Min Act: -0.0001
Data Index: 1075051 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.8160. Min Act: -0.0001
Data Index: 1294467 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5431. Min Range: -2.5431
Max Act: 1.9521. Min Act: -0.0001
Data Index: 97770 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19