Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 37 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8592. Min Act: -0.0001
Data Index: 407013 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8916. Min Act: -0.0001
Data Index: 444859 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8501. Min Act: -0.0001
Data Index: 984408 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8807. Min Act: -0.0001
Data Index: 711198 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8350. Min Act: -0.0001
Data Index: 1297695 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8534. Min Act: -0.0001
Data Index: 1205033 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8420. Min Act: -0.0001
Data Index: 828853 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8696. Min Act: -0.0001
Data Index: 780765 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8518. Min Act: -0.0001
Data Index: 449428 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7717. Min Act: -0.0001
Data Index: 692365 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.8188. Min Act: -0.0001
Data Index: 2210 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7872. Min Act: -0.0001
Data Index: 198634 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7308. Min Act: -0.0001
Data Index: 1089983 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7554. Min Act: -0.0001
Data Index: 1000222 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7189. Min Act: -0.0001
Data Index: 261927 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.6344. Min Act: -0.0001
Data Index: 526590 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7152. Min Act: -0.0001
Data Index: 290816 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7125. Min Act: -0.0001
Data Index: 338240 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.7307. Min Act: -0.0001
Data Index: 960183 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8916. Min Range: -0.8916
Max Act: 0.6951. Min Act: -0.0001
Data Index: 926300 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19