Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.5240. Min Act: -0.0000

Data Index: 257070 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1222775 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4143. Min Act: -0.0000

Data Index: 64092 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1329108 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4779. Min Act: -0.0000

Data Index: 721097 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4644. Min Act: -0.0000

Data Index: 622726 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4469. Min Act: -0.0000

Data Index: 64709 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4343. Min Act: -0.0000

Data Index: 829869 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1015368 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4489. Min Act: -0.0000

Data Index: 400256 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4213. Min Act: -0.0000

Data Index: 566163 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1314100 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4276. Min Act: -0.0000

Data Index: 78669 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3897. Min Act: -0.0000

Data Index: 792163 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4038. Min Act: -0.0000

Data Index: 808482 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4199. Min Act: -0.0000

Data Index: 150731 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3973. Min Act: -0.0000

Data Index: 267360 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4033. Min Act: -0.0000

Data Index: 65163 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3885. Min Act: -0.0000

Data Index: 260071 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3851. Min Act: -0.0000

Data Index: 287922 (C4 (Web Text))

Max Activating Token Index: 724