Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3154 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.9245. Min Act: -0.0001
Data Index: 1251762 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.5990. Min Act: -0.0001
Data Index: 1150760 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.5852. Min Act: -0.0001
Data Index: 1154337 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.5627. Min Act: -0.0001
Data Index: 408592 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.5999. Min Act: -0.0001
Data Index: 403677 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.6869. Min Act: -0.0001
Data Index: 677043 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.5142. Min Act: -0.0001
Data Index: 215300 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.5884. Min Act: -0.0001
Data Index: 1062214 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.2941. Min Act: -0.0001
Data Index: 1325940 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.5166. Min Act: -0.0001
Data Index: 1337425 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.4600. Min Act: -0.0001
Data Index: 460908 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.4731. Min Act: -0.0001
Data Index: 467478 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.4249. Min Act: -0.0001
Data Index: 753102 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.3514. Min Act: -0.0001
Data Index: 645421 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.4947. Min Act: -0.0001
Data Index: 62786 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.3383. Min Act: -0.0001
Data Index: 326070 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.2856. Min Act: -0.0001
Data Index: 1058384 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.3740. Min Act: -0.0001
Data Index: 938070 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.3559. Min Act: -0.0001
Data Index: 1131168 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9245. Min Range: -1.9245
Max Act: 1.3504. Min Act: -0.0001
Data Index: 1310413 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19