Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3406 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.5191. Min Act: -0.0001
Data Index: 141321 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.9810. Min Act: -0.0001
Data Index: 628404 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.1207. Min Act: -0.0001
Data Index: 716159 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.9748. Min Act: -0.0001
Data Index: 538833 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.1780. Min Act: -0.0001
Data Index: 823421 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.0714. Min Act: -0.0001
Data Index: 1024365 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.0620. Min Act: -0.0001
Data Index: 159678 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.8566. Min Act: -0.0001
Data Index: 262011 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.9460. Min Act: -0.0001
Data Index: 1070504 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.9598. Min Act: -0.0001
Data Index: 44737 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.0453. Min Act: -0.0001
Data Index: 277050 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.8018. Min Act: -0.0001
Data Index: 77997 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.0163. Min Act: -0.0001
Data Index: 1300462 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.8573. Min Act: -0.0001
Data Index: 515559 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5191. Min Range: -2.5191
Max Act: 2.0884. Min Act: -0.0001
Data Index: 648979 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.8260. Min Act: -0.0001
Data Index: 1159212 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.6685. Min Act: -0.0001
Data Index: 1302846 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.7960. Min Act: -0.0001
Data Index: 553809 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.6479. Min Act: -0.0001
Data Index: 1338655 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5191. Min Range: -2.5191
Max Act: 1.7643. Min Act: -0.0001
Data Index: 1272517 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19