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

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

Neuron 1887 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2578. Min Act: -0.0000

Data Index: 175631 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1203410 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1118993 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2428. Min Act: -0.0000

Data Index: 839662 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2318. Min Act: -0.0000

Data Index: 212644 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2306. Min Act: -0.0001

Data Index: 365938 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2212. Min Act: -0.0000

Data Index: 761446 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2282. Min Act: -0.0000

Data Index: 307040 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2262. Min Act: -0.0000

Data Index: 39476 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1320784 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2065. Min Act: -0.0001

Data Index: 453421 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2199. Min Act: -0.0001

Data Index: 53073 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1249028 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2146. Min Act: -0.0001

Data Index: 929620 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2126. Min Act: -0.0000

Data Index: 122077 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1506899 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2103. Min Act: -0.0000

Data Index: 527364 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2117. Min Act: -0.0001

Data Index: 504614 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2033. Min Act: -0.0001

Data Index: 728327 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2181. Min Act: -0.0000

Data Index: 503682 (C4 (Web Text))

Max Activating Token Index: 267