Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4313 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6041. Min Act: -0.0001

Data Index: 1127315 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6359. Min Act: -0.0001

Data Index: 1251168 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6189. Min Act: -0.0001

Data Index: 262321 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6115. Min Act: -0.0001

Data Index: 1135098 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6203. Min Act: -0.0001

Data Index: 176699 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1186570 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1175750 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6214. Min Act: -0.0001

Data Index: 419133 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5972. Min Act: -0.0001

Data Index: 159092 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6166. Min Act: -0.0001

Data Index: 338543 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5607. Min Act: -0.0001

Data Index: 1470640 (Python Code)

Max Activating Token Index: 587

Text #11

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5616. Min Act: -0.0001

Data Index: 1218324 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5457. Min Act: -0.0001

Data Index: 546017 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5561. Min Act: -0.0001

Data Index: 1083657 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5697. Min Act: -0.0001

Data Index: 171334 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5499. Min Act: -0.0001

Data Index: 1246435 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5679. Min Act: -0.0001

Data Index: 131739 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5199. Min Act: -0.0001

Data Index: 1180023 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5344. Min Act: -0.0001

Data Index: 943532 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5286. Min Act: -0.0001

Data Index: 1083815 (C4 (Web Text))

Max Activating Token Index: 858