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

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

Neuron 1696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2848. Min Act: -0.0002

Data Index: 1277888 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2344. Min Act: -0.0001

Data Index: 964810 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2484. Min Act: -0.0002

Data Index: 922897 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2479. Min Act: -0.0002

Data Index: 1315561 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2443. Min Act: -0.0002

Data Index: 100449 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2374. Min Act: -0.0002

Data Index: 1088515 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2349. Min Act: -0.0001

Data Index: 215478 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2446. Min Act: -0.0002

Data Index: 916447 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2399. Min Act: -0.0002

Data Index: 526136 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2540. Min Act: -0.0002

Data Index: 484085 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2438. Min Act: -0.0002

Data Index: 721659 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2357. Min Act: -0.0002

Data Index: 1236325 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2442. Min Act: -0.0002

Data Index: 1198181 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2275. Min Act: -0.0001

Data Index: 954041 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2350. Min Act: -0.0001

Data Index: 931412 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2187. Min Act: -0.0002

Data Index: 329968 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2339. Min Act: -0.0002

Data Index: 1012183 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2321. Min Act: -0.0002

Data Index: 346435 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2177. Min Act: -0.0002

Data Index: 535281 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2255. Min Act: -0.0001

Data Index: 165686 (C4 (Web Text))

Max Activating Token Index: 819