Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.6560. Min Act: -0.0000

Data Index: 399868 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.5232. Min Act: -0.0000

Data Index: 705231 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3717. Min Act: -0.0000

Data Index: 1231903 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3208. Min Act: -0.0000

Data Index: 74859 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3902. Min Act: -0.0000

Data Index: 924133 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3373. Min Act: -0.0000

Data Index: 471244 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3322. Min Act: -0.0000

Data Index: 559388 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3675. Min Act: -0.0000

Data Index: 644140 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3245. Min Act: -0.0000

Data Index: 201460 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2570. Min Act: -0.0001

Data Index: 1309092 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1220971 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2172. Min Act: -0.0000

Data Index: 366127 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2178. Min Act: -0.0000

Data Index: 561177 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2029. Min Act: -0.0000

Data Index: 286031 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2675. Min Act: -0.0000

Data Index: 909226 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2136. Min Act: -0.0000

Data Index: 1172933 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.1679. Min Act: -0.0000

Data Index: 786079 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2339. Min Act: -0.0000

Data Index: 545610 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2495. Min Act: -0.0000

Data Index: 903995 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2372. Min Act: -0.0000

Data Index: 982233 (C4 (Web Text))

Max Activating Token Index: 719