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

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

Neuron 2654 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: 1.6878. Min Range: -1.6878

Max Act: 1.6241. Min Act: -0.0001

Data Index: 711787 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.6878. Min Act: -0.0001

Data Index: 408278 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5982. Min Act: -0.0001

Data Index: 769560 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5959. Min Act: -0.0001

Data Index: 1226058 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5397. Min Act: -0.0001

Data Index: 1262339 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5128. Min Act: -0.0001

Data Index: 169990 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5345. Min Act: -0.0001

Data Index: 1283548 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4399. Min Act: -0.0001

Data Index: 460327 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4849. Min Act: -0.0001

Data Index: 436161 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5277. Min Act: -0.0001

Data Index: 125195 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4349. Min Act: -0.0001

Data Index: 118186 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5169. Min Act: -0.0001

Data Index: 709720 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3408. Min Act: -0.0001

Data Index: 150215 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4549. Min Act: -0.0001

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4175. Min Act: -0.0001

Data Index: 111275 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3731. Min Act: -0.0001

Data Index: 757837 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4058. Min Act: -0.0001

Data Index: 1215719 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4448. Min Act: -0.0001

Data Index: 192916 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.2814. Min Act: -0.0001

Data Index: 652284 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3152. Min Act: -0.0001

Data Index: 906953 (C4 (Web Text))

Max Activating Token Index: 310