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

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

Neuron 1826 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2818. Min Act: -0.0000

Data Index: 969880 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2921. Min Act: -0.0001

Data Index: 308304 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2613. Min Act: -0.0000

Data Index: 922614 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1176732 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2389. Min Act: -0.0001

Data Index: 293501 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2287. Min Act: -0.0000

Data Index: 163663 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2181. Min Act: -0.0000

Data Index: 895256 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2245. Min Act: -0.0000

Data Index: 823195 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1056926 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.1949. Min Act: -0.0001

Data Index: 286972 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2268. Min Act: -0.0001

Data Index: 363207 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1022130 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2164. Min Act: -0.0001

Data Index: 683258 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2176. Min Act: -0.0001

Data Index: 667594 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2289. Min Act: -0.0001

Data Index: 371831 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2130. Min Act: -0.0001

Data Index: 850163 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1212858 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1017565 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2178. Min Act: -0.0000

Data Index: 329169 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1050575 (C4 (Web Text))

Max Activating Token Index: 630