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

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

Neuron 1091 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2276. Min Act: -0.0000

Data Index: 778631 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2380. Min Act: -0.0000

Data Index: 465167 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2306. Min Act: -0.0000

Data Index: 802501 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1270955 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2247. Min Act: -0.0000

Data Index: 256180 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1145774 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2220. Min Act: -0.0000

Data Index: 677932 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2220. Min Act: -0.0000

Data Index: 707821 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1332134 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2201. Min Act: -0.0000

Data Index: 964826 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2052. Min Act: -0.0000

Data Index: 104908 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2029. Min Act: -0.0000

Data Index: 535707 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2123. Min Act: -0.0000

Data Index: 724766 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1041669 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2075. Min Act: -0.0000

Data Index: 569678 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1400234 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1972. Min Act: -0.0000

Data Index: 757732 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1722. Min Act: -0.0000

Data Index: 970148 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1940. Min Act: -0.0000

Data Index: 152374 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2045. Min Act: -0.0000

Data Index: 318915 (C4 (Web Text))

Max Activating Token Index: 813