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

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

Neuron 4813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5477. Min Act: -0.0000

Data Index: 23140 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.6194. Min Act: -0.0001

Data Index: 1268886 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5934. Min Act: -0.0000

Data Index: 508595 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5315. Min Act: -0.0000

Data Index: 430207 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5717. Min Act: -0.0000

Data Index: 269344 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1208497 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5838. Min Act: -0.0000

Data Index: 192074 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5350. Min Act: -0.0001

Data Index: 548574 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5431. Min Act: -0.0000

Data Index: 694120 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1004180 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5298. Min Act: -0.0001

Data Index: 1033766 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1030460 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5352. Min Act: -0.0000

Data Index: 396157 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5194. Min Act: -0.0000

Data Index: 411925 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5166. Min Act: -0.0001

Data Index: 1148089 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1031426 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1094589 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1197196 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4715. Min Act: -0.0000

Data Index: 817398 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1133888 (C4 (Web Text))

Max Activating Token Index: 91