Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1248 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2284. Min Act: -0.0000

Data Index: 37418 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2348. Min Act: -0.0000

Data Index: 970276 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2272. Min Act: -0.0000

Data Index: 433718 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2150. Min Act: -0.0000

Data Index: 113609 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1332535 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2112. Min Act: -0.0000

Data Index: 935391 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2286. Min Act: -0.0000

Data Index: 785248 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1220139 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1143887 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1230377 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1992. Min Act: -0.0000

Data Index: 314641 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2055. Min Act: -0.0000

Data Index: 149851 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1945. Min Act: -0.0000

Data Index: 853597 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2140. Min Act: -0.0000

Data Index: 255846 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1981. Min Act: -0.0000

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1060869 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1954. Min Act: -0.0000

Data Index: 607760 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1955. Min Act: -0.0000

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1939. Min Act: -0.0000

Data Index: 358814 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1932. Min Act: -0.0000

Data Index: 165173 (C4 (Web Text))

Max Activating Token Index: 461