Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 291 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.9704. Min Act: -0.0001
Data Index: 1075624 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.9180. Min Act: -0.0001
Data Index: 1543593 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8710. Min Act: -0.0001
Data Index: 1152710 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.9055. Min Act: -0.0001
Data Index: 1021537 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8305. Min Act: -0.0001
Data Index: 465007 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8879. Min Act: -0.0001
Data Index: 102050 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8474. Min Act: -0.0001
Data Index: 1019852 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8244. Min Act: -0.0001
Data Index: 95327 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7926. Min Act: -0.0001
Data Index: 386902 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8805. Min Act: -0.0001
Data Index: 41824 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8393. Min Act: -0.0001
Data Index: 231539 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7318. Min Act: -0.0001
Data Index: 24584 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7660. Min Act: -0.0001
Data Index: 1271734 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8057. Min Act: -0.0001
Data Index: 970193 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.8044. Min Act: -0.0001
Data Index: 1418889 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7988. Min Act: -0.0001
Data Index: 417830 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7653. Min Act: -0.0001
Data Index: 207360 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7485. Min Act: -0.0001
Data Index: 910674 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7122. Min Act: -0.0001
Data Index: 27694 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9704. Min Range: -0.9704
Max Act: 0.7382. Min Act: -0.0001
Data Index: 294721 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19