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

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

Neuron 4085 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2346. Min Range: -1.2346

Max Act: 1.1644. Min Act: -0.0000

Data Index: 741882 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.2346. Min Range: -1.2346

Max Act: 1.2197. Min Act: -0.0000

Data Index: 1041573 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.2346. Min Range: -1.2346

Max Act: 1.2346. Min Act: -0.0000

Data Index: 411937 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.2346. Min Range: -1.2346

Max Act: 1.0892. Min Act: -0.0000

Data Index: 918245 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 1.2346. Min Range: -1.2346

Max Act: 1.0542. Min Act: -0.0000

Data Index: 860533 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.9360. Min Act: -0.0000

Data Index: 897089 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1152845 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.8970. Min Act: -0.0000

Data Index: 547388 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.8742. Min Act: -0.0000

Data Index: 727104 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.8378. Min Act: -0.0000

Data Index: 287389 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1208507 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1057680 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1052000 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.7356. Min Act: -0.0000

Data Index: 752359 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.7164. Min Act: -0.0000

Data Index: 642217 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.7314. Min Act: -0.0000

Data Index: 699975 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.6874. Min Act: -0.0000

Data Index: 9682 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.6699. Min Act: -0.0000

Data Index: 279580 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.6837. Min Act: -0.0000

Data Index: 589194 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.2346. Min Range: -1.2346

Max Act: 0.7168. Min Act: -0.0000

Data Index: 378633 (C4 (Web Text))

Max Activating Token Index: 841