Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1872 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2617. Min Act: -0.0001

Data Index: 947695 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2457. Min Act: -0.0001

Data Index: 798538 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2461. Min Act: -0.0001

Data Index: 480691 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1064312 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2381. Min Act: -0.0001

Data Index: 993252 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2397. Min Act: -0.0001

Data Index: 1128579 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1057004 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2303. Min Act: -0.0001

Data Index: 697412 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1274799 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2244. Min Act: -0.0001

Data Index: 538875 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2242. Min Act: -0.0001

Data Index: 559911 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2230. Min Act: -0.0001

Data Index: 708617 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1218757 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2218. Min Act: -0.0001

Data Index: 9349 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2161. Min Act: -0.0001

Data Index: 164009 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2145. Min Act: -0.0001

Data Index: 235072 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2159. Min Act: -0.0001

Data Index: 867657 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2190. Min Act: -0.0001

Data Index: 315001 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2127. Min Act: -0.0001

Data Index: 685245 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1089662 (C4 (Web Text))

Max Activating Token Index: 87