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

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

Neuron 1155 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: 0.2585. Min Range: -0.2585

Max Act: 0.2580. Min Act: -0.0000

Data Index: 617966 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2585. Min Act: -0.0000

Data Index: 29103 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1166949 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1027892 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2356. Min Act: -0.0001

Data Index: 1476402 (Python Code)

Max Activating Token Index: 791

Text #5

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2179. Min Act: -0.0000

Data Index: 17153 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2319. Min Act: -0.0000

Data Index: 481868 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2150. Min Act: -0.0000

Data Index: 121873 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2134. Min Act: -0.0000

Data Index: 715120 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1598601 (Python Code)

Max Activating Token Index: 223

Text #10

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2153. Min Act: -0.0001

Data Index: 1000315 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1163618 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2197. Min Act: -0.0001

Data Index: 1060117 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2255. Min Act: -0.0000

Data Index: 553858 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2100. Min Act: -0.0001

Data Index: 877008 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1370537 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1220352 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1543467 (Python Code)

Max Activating Token Index: 398

Text #18

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1998. Min Act: -0.0000

Data Index: 633395 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1468631 (Python Code)

Max Activating Token Index: 773