Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1072 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1490104 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2957. Min Act: -0.0001

Data Index: 600409 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2344. Min Act: -0.0001

Data Index: 159825 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.3086. Min Act: -0.0001

Data Index: 1409163 (Python Code)

Max Activating Token Index: 991

Text #4

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2934. Min Act: -0.0001

Data Index: 1022885 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2677. Min Act: -0.0000

Data Index: 442650 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2203. Min Act: -0.0001

Data Index: 1514390 (Python Code)

Max Activating Token Index: 658

Text #7

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1558601 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1555080 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2274. Min Act: -0.0001

Data Index: 388768 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1313505 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2300. Min Act: -0.0001

Data Index: 237923 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2372. Min Act: -0.0001

Data Index: 823039 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2544. Min Act: -0.0001

Data Index: 596430 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2100. Min Act: -0.0000

Data Index: 618227 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2291. Min Act: -0.0001

Data Index: 614631 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1423185 (Python Code)

Max Activating Token Index: 359

Text #17

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2175. Min Act: -0.0001

Data Index: 964524 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2275. Min Act: -0.0001

Data Index: 256181 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2418. Min Act: -0.0001

Data Index: 643981 (C4 (Web Text))

Max Activating Token Index: 448