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

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

Neuron 3429 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8092. Min Range: -2.8092

Max Act: 2.8092. Min Act: -0.0000

Data Index: 611466 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 2.8092. Min Range: -2.8092

Max Act: 2.0864. Min Act: -0.0000

Data Index: 170019 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 2.8092. Min Range: -2.8092

Max Act: 2.0668. Min Act: -0.0000

Data Index: 1316183 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.8241. Min Act: -0.0000

Data Index: 609865 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.7961. Min Act: -0.0000

Data Index: 178098 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.7684. Min Act: -0.0000

Data Index: 671892 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.9036. Min Act: -0.0000

Data Index: 127352 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.7221. Min Act: -0.0000

Data Index: 291258 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.8294. Min Act: -0.0000

Data Index: 766282 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.7721. Min Act: -0.0000

Data Index: 299386 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1201325 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.7162. Min Act: -0.0000

Data Index: 199074 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.7067. Min Act: -0.0000

Data Index: 615260 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.6069. Min Act: -0.0000

Data Index: 101042 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1060316 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.4846. Min Act: -0.0000

Data Index: 884761 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.7334. Min Act: -0.0000

Data Index: 522666 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.4862. Min Act: -0.0000

Data Index: 186615 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.4515. Min Act: -0.0000

Data Index: 991536 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 2.8092. Min Range: -2.8092

Max Act: 1.4584. Min Act: -0.0000

Data Index: 635092 (C4 (Web Text))

Max Activating Token Index: 531