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

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

Neuron 891 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.2159. Min Act: -0.0001

Data Index: 1053269 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1216. Min Act: -0.0001

Data Index: 748381 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1662. Min Act: -0.0001

Data Index: 364170 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9867. Min Act: -0.0001

Data Index: 551974 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9296. Min Act: -0.0001

Data Index: 1175146 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8478. Min Act: -0.0001

Data Index: 117885 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9478. Min Act: -0.0001

Data Index: 910432 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0196. Min Act: -0.0001

Data Index: 229213 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9502. Min Act: -0.0001

Data Index: 150153 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8862. Min Act: -0.0001

Data Index: 496529 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8357. Min Act: -0.0001

Data Index: 161317 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8842. Min Act: -0.0001

Data Index: 300424 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8805. Min Act: -0.0001

Data Index: 982905 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8959. Min Act: -0.0001

Data Index: 1300899 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8494. Min Act: -0.0001

Data Index: 1248516 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9021. Min Act: -0.0001

Data Index: 841952 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8682. Min Act: -0.0001

Data Index: 351823 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8488. Min Act: -0.0001

Data Index: 203348 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8989. Min Act: -0.0001

Data Index: 99927 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8964. Min Act: -0.0001

Data Index: 564004 (C4 (Web Text))

Max Activating Token Index: 329