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

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

Neuron 4958 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6274. Min Range: -4.6274

Max Act: 4.6274. Min Act: -0.0000

Data Index: 473557 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 4.6274. Min Range: -4.6274

Max Act: 4.3079. Min Act: -0.0000

Data Index: 411060 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 4.6274. Min Range: -4.6274

Max Act: 4.0294. Min Act: -0.0000

Data Index: 966095 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 4.6274. Min Range: -4.6274

Max Act: 4.1251. Min Act: -0.0000

Data Index: 168593 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.5022. Min Act: -0.0000

Data Index: 626425 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.2236. Min Act: -0.0000

Data Index: 1049989 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.5381. Min Act: -0.0000

Data Index: 1253661 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.2160. Min Act: -0.0000

Data Index: 815543 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.0620. Min Act: -0.0000

Data Index: 849422 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.2107. Min Act: -0.0000

Data Index: 1114355 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.3043. Min Act: -0.0000

Data Index: 1016414 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.1772. Min Act: -0.0000

Data Index: 971644 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 4.6274. Min Range: -4.6274

Max Act: 3.1393. Min Act: -0.0000

Data Index: 1321780 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 4.6274. Min Range: -4.6274

Max Act: 2.8208. Min Act: -0.0000

Data Index: 824788 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 4.6274. Min Range: -4.6274

Max Act: 2.9307. Min Act: -0.0000

Data Index: 1425668 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 4.6274. Min Range: -4.6274

Max Act: 2.7847. Min Act: -0.0000

Data Index: 360015 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 4.6274. Min Range: -4.6274

Max Act: 2.9033. Min Act: -0.0000

Data Index: 1337811 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 4.6274. Min Range: -4.6274

Max Act: 2.6418. Min Act: -0.0000

Data Index: 1058035 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 4.6274. Min Range: -4.6274

Max Act: 2.7173. Min Act: -0.0000

Data Index: 1283228 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 4.6274. Min Range: -4.6274

Max Act: 2.7198. Min Act: -0.0000

Data Index: 947254 (C4 (Web Text))

Max Activating Token Index: 664