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

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

Neuron 3512 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2207. Min Range: -1.2207

Max Act: 1.2207. Min Act: -0.0001

Data Index: 102910 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.2207. Min Range: -1.2207

Max Act: 1.0857. Min Act: -0.0001

Data Index: 1010652 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.9486. Min Act: -0.0001

Data Index: 1206701 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.9230. Min Act: -0.0001

Data Index: 620514 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.9134. Min Act: -0.0001

Data Index: 844411 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8548. Min Act: -0.0001

Data Index: 633361 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8927. Min Act: -0.0001

Data Index: 891332 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8555. Min Act: -0.0001

Data Index: 539118 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8628. Min Act: -0.0001

Data Index: 772540 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8239. Min Act: -0.0001

Data Index: 214577 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.7920. Min Act: -0.0001

Data Index: 691103 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8077. Min Act: -0.0001

Data Index: 763436 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8146. Min Act: -0.0001

Data Index: 347625 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.8824. Min Act: -0.0001

Data Index: 987556 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.7990. Min Act: -0.0001

Data Index: 1145373 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1099218 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.7378. Min Act: -0.0001

Data Index: 977080 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.7727. Min Act: -0.0001

Data Index: 1248111 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.7548. Min Act: -0.0001

Data Index: 630806 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.2207. Min Range: -1.2207

Max Act: 0.7537. Min Act: -0.0001

Data Index: 1312523 (C4 (Web Text))

Max Activating Token Index: 42