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

Dataset: The Pile

Neuron 2994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3950. Min Act: -0.0000

Data Index: 316104 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1581361 (The Pile)

Max Activating Token Index: 907

Text #2

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2244. Min Act: -0.0000

Data Index: 184761 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1653858 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2504. Min Act: -0.0000

Data Index: 22827 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1978210 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2344. Min Act: -0.0000

Data Index: 841367 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1368986 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1586671 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2341. Min Act: -0.0000

Data Index: 306539 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2241. Min Act: -0.0000

Data Index: 428607 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1243023 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2203. Min Act: -0.0000

Data Index: 131162 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2125. Min Act: -0.0000

Data Index: 291356 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1183482 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1529401 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2227. Min Act: -0.0000

Data Index: 924402 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1286638 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1890470 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1915099 (The Pile)

Max Activating Token Index: 685