Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 130 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1324828 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1143. Min Act: -0.0001

Data Index: 330507 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1010. Min Act: -0.0000

Data Index: 900624 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0961. Min Act: -0.0000

Data Index: 739327 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0916. Min Act: -0.0001

Data Index: 750441 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0881. Min Act: -0.0000

Data Index: 496109 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1279566 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1274365 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1302648 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1224456 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1013114 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1223786 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0846. Min Act: -0.0000

Data Index: 380357 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0779. Min Act: -0.0000

Data Index: 111336 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1145428 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0791. Min Act: -0.0001

Data Index: 94354 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0814. Min Act: -0.0000

Data Index: 118172 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1327925 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1132023 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0801. Min Act: -0.0000

Data Index: 838572 (C4 (Web Text))

Max Activating Token Index: 815