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

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

Neuron 3127 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3357. Min Act: -0.0001

Data Index: 199030 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2958. Min Act: -0.0001

Data Index: 959135 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3069. Min Act: -0.0001

Data Index: 1152084 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2630. Min Act: -0.0001

Data Index: 587586 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2647. Min Act: -0.0001

Data Index: 710391 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2451. Min Act: -0.0001

Data Index: 1119537 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1019724 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2495. Min Act: -0.0001

Data Index: 845501 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2239. Min Act: -0.0001

Data Index: 443077 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2295. Min Act: -0.0001

Data Index: 301247 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2438. Min Act: -0.0001

Data Index: 421557 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1007448 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2442. Min Act: -0.0001

Data Index: 880586 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2342. Min Act: -0.0001

Data Index: 412518 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1359293 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2143. Min Act: -0.0001

Data Index: 784768 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2247. Min Act: -0.0001

Data Index: 34674 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2318. Min Act: -0.0001

Data Index: 623602 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2234. Min Act: -0.0001

Data Index: 322526 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2244. Min Act: -0.0001

Data Index: 251427 (C4 (Web Text))

Max Activating Token Index: 747