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

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

Neuron 4183 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1042618 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.4285. Min Act: -0.0000

Data Index: 408274 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.3310. Min Act: -0.0000

Data Index: 566264 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.4124. Min Act: -0.0000

Data Index: 36411 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.3946. Min Act: -0.0000

Data Index: 209062 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2872. Min Act: -0.0000

Data Index: 918207 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1044705 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.3272. Min Act: -0.0000

Data Index: 668986 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2539. Min Act: 0.0000

Data Index: 266230 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2293. Min Act: -0.0000

Data Index: 41737 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2988. Min Act: -0.0000

Data Index: 535574 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2278. Min Act: -0.0000

Data Index: 732794 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2151. Min Act: -0.0000

Data Index: 972495 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1949. Min Act: -0.0000

Data Index: 460139 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1891. Min Act: -0.0000

Data Index: 297519 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1205747 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1117569 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1894. Min Act: -0.0000

Data Index: 977486 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0450. Min Act: -0.0000

Data Index: 91536 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0277. Min Act: -0.0000

Data Index: 798317 (C4 (Web Text))

Max Activating Token Index: 311