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

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

Neuron 462 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: 0.2624. Min Range: -0.2624

Max Act: 0.2550. Min Act: -0.0000

Data Index: 886824 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2624. Min Act: -0.0000

Data Index: 111873 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2510. Min Act: -0.0001

Data Index: 160366 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2356. Min Act: -0.0000

Data Index: 267948 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2334. Min Act: -0.0000

Data Index: 955272 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2307. Min Act: -0.0001

Data Index: 253643 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2219. Min Act: -0.0001

Data Index: 129628 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2264. Min Act: -0.0001

Data Index: 795329 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1233101 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2255. Min Act: -0.0000

Data Index: 277954 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2247. Min Act: -0.0001

Data Index: 695924 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2137. Min Act: -0.0001

Data Index: 366616 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2193. Min Act: -0.0000

Data Index: 952271 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2235. Min Act: -0.0000

Data Index: 188479 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2060. Min Act: -0.0000

Data Index: 193465 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2224. Min Act: -0.0001

Data Index: 523519 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2143. Min Act: -0.0001

Data Index: 342972 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1236948 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2174. Min Act: -0.0001

Data Index: 16524 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2109. Min Act: -0.0001

Data Index: 937139 (C4 (Web Text))

Max Activating Token Index: 866