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

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

Neuron 3121 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: 1.3206. Min Range: -1.3206

Max Act: 1.2535. Min Act: -0.0001

Data Index: 623516 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1598. Min Act: -0.0001

Data Index: 477190 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.3206. Min Act: -0.0001

Data Index: 249964 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1007. Min Act: -0.0001

Data Index: 1029085 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.2805. Min Act: -0.0001

Data Index: 329937 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1680. Min Act: -0.0001

Data Index: 304144 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0998. Min Act: -0.0001

Data Index: 743529 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0751. Min Act: -0.0001

Data Index: 434535 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0973. Min Act: -0.0001

Data Index: 870496 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0977. Min Act: -0.0001

Data Index: 459437 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0184. Min Act: -0.0000

Data Index: 213540 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1008712 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0751. Min Act: -0.0000

Data Index: 162550 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0425. Min Act: -0.0001

Data Index: 426046 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0165. Min Act: -0.0001

Data Index: 1303195 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.3206. Min Range: -1.3206

Max Act: 0.9849. Min Act: -0.0001

Data Index: 182089 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1161. Min Act: -0.0001

Data Index: 1283720 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.3206. Min Range: -1.3206

Max Act: 0.9601. Min Act: -0.0001

Data Index: 534270 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0264. Min Act: -0.0001

Data Index: 125978 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.3206. Min Range: -1.3206

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1232393 (C4 (Web Text))

Max Activating Token Index: 680