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

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

Neuron 725 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: 1.1448. Min Range: -1.1448

Max Act: 1.1448. Min Act: -0.0001

Data Index: 250668 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9673. Min Act: -0.0001

Data Index: 1280207 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8201. Min Act: -0.0001

Data Index: 223900 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.7949. Min Act: -0.0001

Data Index: 915779 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.7226. Min Act: -0.0001

Data Index: 119678 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.7134. Min Act: -0.0001

Data Index: 666964 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.7683. Min Act: -0.0001

Data Index: 541665 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6536. Min Act: -0.0001

Data Index: 304952 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6691. Min Act: -0.0001

Data Index: 664862 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.5513. Min Act: -0.0001

Data Index: 473233 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6313. Min Act: -0.0001

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6496. Min Act: -0.0001

Data Index: 506150 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6304. Min Act: -0.0001

Data Index: 663212 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6691. Min Act: -0.0001

Data Index: 243255 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.6250. Min Act: -0.0001

Data Index: 642300 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.5963. Min Act: -0.0001

Data Index: 455415 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.5709. Min Act: -0.0001

Data Index: 940655 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1352694 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.5764. Min Act: -0.0001

Data Index: 300802 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.5594. Min Act: -0.0001

Data Index: 92235 (C4 (Web Text))

Max Activating Token Index: 509