Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 684 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0003

Data Index: 592404 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1309169 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0319. Min Act: -0.0003

Data Index: 840645 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0321. Min Act: -0.0003

Data Index: 958376 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0284. Min Act: -0.0003

Data Index: 905789 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0317. Min Act: -0.0003

Data Index: 668524 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0320. Min Act: -0.0003

Data Index: 286288 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0297. Min Act: -0.0003

Data Index: 287139 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1169131 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1076229 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0274. Min Act: -0.0003

Data Index: 10114 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0314. Min Act: -0.0003

Data Index: 524935 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0271. Min Act: -0.0003

Data Index: 882750 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0309. Min Act: -0.0003

Data Index: 229281 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1047270 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0281. Min Act: -0.0003

Data Index: 643243 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1198509 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0317. Min Act: -0.0003

Data Index: 660025 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0296. Min Act: -0.0003

Data Index: 296528 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1204607 (C4 (Web Text))

Max Activating Token Index: 971