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

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

Neuron 1027 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.6217. Min Act: -0.0001

Data Index: 1088136 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.6430. Min Act: -0.0001

Data Index: 225201 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.6029. Min Act: -0.0001

Data Index: 958985 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5704. Min Act: -0.0001

Data Index: 992404 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1096303 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5318. Min Act: -0.0001

Data Index: 1062420 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5587. Min Act: -0.0001

Data Index: 1217121 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5767. Min Act: -0.0001

Data Index: 59960 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1131878 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5529. Min Act: -0.0001

Data Index: 371699 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5181. Min Act: -0.0001

Data Index: 270742 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5659. Min Act: -0.0001

Data Index: 257225 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5465. Min Act: -0.0001

Data Index: 726968 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5450. Min Act: -0.0001

Data Index: 74761 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5450. Min Act: -0.0001

Data Index: 901066 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5414. Min Act: -0.0001

Data Index: 926147 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5371. Min Act: -0.0001

Data Index: 208604 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5180. Min Act: -0.0001

Data Index: 341800 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5300. Min Act: -0.0001

Data Index: 274804 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5340. Min Act: -0.0001

Data Index: 547769 (C4 (Web Text))

Max Activating Token Index: 517