Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1845 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0005

Data Index: 1015991 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0241. Min Act: -0.0005

Data Index: 1150279 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0243. Min Act: -0.0005

Data Index: 851174 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0243. Min Act: -0.0004

Data Index: 774894 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1619270 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0239. Min Act: -0.0005

Data Index: 481943 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0005

Data Index: 642250 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0005

Data Index: 29031 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0230. Min Act: -0.0005

Data Index: 947895 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0233. Min Act: -0.0005

Data Index: 1219182 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0223. Min Act: -0.0005

Data Index: 1317495 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0232. Min Act: -0.0005

Data Index: 471859 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0226. Min Act: -0.0005

Data Index: 618608 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0005

Data Index: 1218819 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0228. Min Act: -0.0005

Data Index: 562644 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0223. Min Act: -0.0005

Data Index: 766248 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0223. Min Act: -0.0005

Data Index: 486657 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0005

Data Index: 1561992 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0226. Min Act: -0.0005

Data Index: 5508 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0222. Min Act: -0.0005

Data Index: 232443 (C4 (Web Text))

Max Activating Token Index: 860