Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3552 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.8241. Min Act: -0.0001
Data Index: 719977 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.8173. Min Act: -0.0001
Data Index: 988447 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.8419. Min Act: -0.0001
Data Index: 258128 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7389. Min Act: -0.0001
Data Index: 415733 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7952. Min Act: -0.0001
Data Index: 843790 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7752. Min Act: -0.0001
Data Index: 1009700 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7241. Min Act: -0.0001
Data Index: 754915 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7152. Min Act: -0.0001
Data Index: 286765 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.6593. Min Act: -0.0001
Data Index: 451915 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7095. Min Act: -0.0001
Data Index: 1115566 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7377. Min Act: -0.0001
Data Index: 1253181 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.6794. Min Act: -0.0001
Data Index: 958373 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7437. Min Act: -0.0001
Data Index: 111714 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7334. Min Act: -0.0001
Data Index: 455244 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.6663. Min Act: -0.0001
Data Index: 851959 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7195. Min Act: -0.0001
Data Index: 191259 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7177. Min Act: -0.0001
Data Index: 1125808 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.6906. Min Act: -0.0001
Data Index: 329112 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.7209. Min Act: -0.0001
Data Index: 443404 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8419. Min Range: -0.8419
Max Act: 0.6724. Min Act: -0.0001
Data Index: 1331020 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19