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

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

Neuron 4033 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: 0.3188. Min Range: -0.3188

Max Act: 0.3056. Min Act: -0.0000

Data Index: 652647 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.3176. Min Act: -0.0000

Data Index: 552831 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.3188. Min Act: -0.0000

Data Index: 197225 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1296064 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1465635 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2765. Min Act: -0.0000

Data Index: 311521 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1128562 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2643. Min Act: -0.0000

Data Index: 805809 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2580. Min Act: -0.0000

Data Index: 1092563 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2371. Min Act: -0.0000

Data Index: 655466 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1487832 (Python Code)

Max Activating Token Index: 652

Text #11

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2148. Min Act: -0.0000

Data Index: 502420 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2366. Min Act: -0.0000

Data Index: 278013 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1024947 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1566311 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1615167 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2188. Min Act: -0.0000

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2202. Min Act: -0.0000

Data Index: 378155 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2201. Min Act: -0.0000

Data Index: 967753 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.3188. Min Range: -0.3188

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1191861 (C4 (Web Text))

Max Activating Token Index: 528