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

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

Neuron 1966 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: 3.4599. Min Range: -3.4599

Max Act: 3.4599. Min Act: -0.0001

Data Index: 1223469 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.9175. Min Act: -0.0000

Data Index: 429920 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.5550. Min Act: -0.0001

Data Index: 799819 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.3062. Min Act: -0.0001

Data Index: 900167 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.4096. Min Act: -0.0000

Data Index: 1359100 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.3833. Min Act: -0.0001

Data Index: 1137671 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.2353. Min Act: -0.0001

Data Index: 1101544 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.3326. Min Act: -0.0001

Data Index: 292773 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.2679. Min Act: -0.0001

Data Index: 1183900 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.3780. Min Act: -0.0001

Data Index: 185669 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.2673. Min Act: -0.0001

Data Index: 200465 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.0400. Min Act: -0.0001

Data Index: 60077 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.2234. Min Act: -0.0001

Data Index: 722926 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.0009. Min Act: -0.0001

Data Index: 1171140 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.0376. Min Act: -0.0001

Data Index: 1312771 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.1384. Min Act: -0.0001

Data Index: 449492 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.0343. Min Act: -0.0001

Data Index: 961095 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.1256. Min Act: -0.0001

Data Index: 480933 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.0232. Min Act: -0.0000

Data Index: 107459 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.0010. Min Act: -0.0001

Data Index: 112524 (C4 (Web Text))

Max Activating Token Index: 935