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

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

Neuron 789 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3171. Min Range: -3.3171

Max Act: 3.3171. Min Act: -0.0000

Data Index: 846580 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.3171. Min Range: -3.3171

Max Act: 3.0872. Min Act: -0.0000

Data Index: 1046681 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.9667. Min Act: -0.0000

Data Index: 352931 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.8231. Min Act: -0.0000

Data Index: 1132070 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.8365. Min Act: -0.0000

Data Index: 330500 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.9546. Min Act: -0.0000

Data Index: 146254 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.6487. Min Act: -0.0000

Data Index: 382292 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.7721. Min Act: -0.0000

Data Index: 1267264 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.7296. Min Act: -0.0000

Data Index: 309057 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.6670. Min Act: -0.0000

Data Index: 953967 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.4747. Min Act: -0.0000

Data Index: 1058443 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1140122 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.5238. Min Act: -0.0000

Data Index: 202520 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.4923. Min Act: -0.0000

Data Index: 942777 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.4692. Min Act: -0.0000

Data Index: 874338 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.3397. Min Act: -0.0000

Data Index: 1290702 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.3132. Min Act: -0.0000

Data Index: 1308450 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.4408. Min Act: -0.0000

Data Index: 168378 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.4301. Min Act: -0.0000

Data Index: 106733 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.3171. Min Range: -3.3171

Max Act: 2.2889. Min Act: -0.0000

Data Index: 1098371 (C4 (Web Text))

Max Activating Token Index: 87