Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1137 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5202. Min Range: -2.5202
Max Act: 2.5202. Min Act: -0.0001
Data Index: 89269 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5202. Min Range: -2.5202
Max Act: 2.3654. Min Act: -0.0001
Data Index: 376035 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5202. Min Range: -2.5202
Max Act: 2.1377. Min Act: -0.0001
Data Index: 378722 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5202. Min Range: -2.5202
Max Act: 2.2184. Min Act: -0.0001
Data Index: 106326 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5202. Min Range: -2.5202
Max Act: 2.1194. Min Act: -0.0001
Data Index: 446560 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5202. Min Range: -2.5202
Max Act: 2.1151. Min Act: -0.0001
Data Index: 1174540 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.8776. Min Act: -0.0001
Data Index: 1109111 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.9621. Min Act: -0.0001
Data Index: 627314 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5202. Min Range: -2.5202
Max Act: 2.0345. Min Act: -0.0001
Data Index: 461719 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.7037. Min Act: -0.0001
Data Index: 347991 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.4980. Min Act: -0.0001
Data Index: 172290 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.8368. Min Act: -0.0001
Data Index: 1161848 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.8283. Min Act: -0.0001
Data Index: 1165321 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.7937. Min Act: -0.0001
Data Index: 633718 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.7896. Min Act: -0.0001
Data Index: 42920 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.6692. Min Act: -0.0001
Data Index: 463117 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.8663. Min Act: -0.0001
Data Index: 1317989 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.6697. Min Act: -0.0001
Data Index: 1141472 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.8432. Min Act: -0.0001
Data Index: 270387 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5202. Min Range: -2.5202
Max Act: 1.7538. Min Act: -0.0001
Data Index: 336540 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19