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

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

Neuron 4359 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.6310. Min Act: -0.0000

Data Index: 882332 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.4154. Min Act: -0.0000

Data Index: 307704 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.3345. Min Act: -0.0000

Data Index: 487214 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2263. Min Act: -0.0000

Data Index: 986391 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2096. Min Act: -0.0000

Data Index: 931184 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1312. Min Act: -0.0000

Data Index: 506798 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1436503 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1977. Min Act: -0.0001

Data Index: 287014 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2452. Min Act: -0.0000

Data Index: 473503 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1959. Min Act: -0.0000

Data Index: 160279 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1610107 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1191809 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.0603. Min Act: -0.0000

Data Index: 810948 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.0232. Min Act: -0.0001

Data Index: 622648 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.0101. Min Act: -0.0000

Data Index: 198702 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.6310. Min Range: -1.6310

Max Act: 0.8931. Min Act: -0.0000

Data Index: 806987 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.6310. Min Range: -1.6310

Max Act: 0.9456. Min Act: -0.0000

Data Index: 407052 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.0319. Min Act: -0.0000

Data Index: 749104 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1385194 (Python Code)

Max Activating Token Index: 11