Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6103 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2811. Min Act: -0.0000

Data Index: 382924 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1138288 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2533. Min Act: -0.0000

Data Index: 923255 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2618. Min Act: -0.0000

Data Index: 606060 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2462. Min Act: -0.0000

Data Index: 734600 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2552. Min Act: -0.0000

Data Index: 231651 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1259027 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2183. Min Act: -0.0001

Data Index: 1331940 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1301327 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2328. Min Act: -0.0000

Data Index: 179483 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2244. Min Act: -0.0000

Data Index: 352841 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2267. Min Act: -0.0000

Data Index: 942263 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2224. Min Act: -0.0000

Data Index: 237808 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1047630 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2066. Min Act: -0.0001

Data Index: 29048 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2146. Min Act: -0.0000

Data Index: 850050 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2265. Min Act: -0.0000

Data Index: 712225 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2149. Min Act: -0.0001

Data Index: 112678 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2150. Min Act: -0.0000

Data Index: 899364 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2091. Min Act: -0.0000

Data Index: 257935 (C4 (Web Text))

Max Activating Token Index: 659