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

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

Neuron 2250 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: 0.3916. Min Range: -0.3916

Max Act: 0.3720. Min Act: -0.0001

Data Index: 371699 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3705. Min Act: -0.0001

Data Index: 551600 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3691. Min Act: -0.0001

Data Index: 798288 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3566. Min Act: -0.0001

Data Index: 721912 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3916. Min Act: -0.0001

Data Index: 1232218 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1445953 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3751. Min Act: -0.0001

Data Index: 316499 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3405. Min Act: -0.0001

Data Index: 943466 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3208. Min Act: -0.0001

Data Index: 848638 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3283. Min Act: -0.0001

Data Index: 733093 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3355. Min Act: -0.0001

Data Index: 764870 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3363. Min Act: -0.0001

Data Index: 303676 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3222. Min Act: -0.0001

Data Index: 87636 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3222. Min Act: -0.0001

Data Index: 896224 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1031022 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3359. Min Act: -0.0001

Data Index: 733223 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1209862 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3224. Min Act: -0.0000

Data Index: 589118 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3246. Min Act: -0.0001

Data Index: 1286615 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3122. Min Act: -0.0001

Data Index: 790663 (C4 (Web Text))

Max Activating Token Index: 300