Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1852 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2620. Min Act: -0.0001

Data Index: 300436 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2499. Min Act: -0.0001

Data Index: 775457 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2564. Min Act: -0.0001

Data Index: 1270421 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2512. Min Act: -0.0000

Data Index: 546542 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1140089 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2471. Min Act: -0.0000

Data Index: 365879 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2371. Min Act: -0.0001

Data Index: 515737 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2381. Min Act: -0.0000

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2344. Min Act: -0.0001

Data Index: 1110592 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2286. Min Act: -0.0001

Data Index: 913795 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1215431 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2168. Min Act: -0.0000

Data Index: 202143 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2239. Min Act: -0.0000

Data Index: 987704 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1262236 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2179. Min Act: -0.0001

Data Index: 873488 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2190. Min Act: -0.0001

Data Index: 863194 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2168. Min Act: -0.0000

Data Index: 995274 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1149247 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2161. Min Act: -0.0001

Data Index: 487996 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2078. Min Act: -0.0001

Data Index: 884187 (C4 (Web Text))

Max Activating Token Index: 788