Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2641 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9763. Min Act: -0.0003

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8733. Min Act: -0.0003

Data Index: 474811 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9678. Min Act: -0.0003

Data Index: 1083793 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8579. Min Act: -0.0003

Data Index: 71172 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7420. Min Act: -0.0003

Data Index: 762648 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8271. Min Act: -0.0003

Data Index: 859181 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6458. Min Act: -0.0003

Data Index: 1307879 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8318. Min Act: -0.0003

Data Index: 1216513 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6918. Min Act: -0.0003

Data Index: 692974 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6012. Min Act: -0.0003

Data Index: 1079280 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7483. Min Act: -0.0003

Data Index: 166460 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7655. Min Act: -0.0003

Data Index: 855235 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7640. Min Act: -0.0003

Data Index: 1178454 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7138. Min Act: -0.0003

Data Index: 723365 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6901. Min Act: -0.0003

Data Index: 996285 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7550. Min Act: -0.0003

Data Index: 213832 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7306. Min Act: -0.0003

Data Index: 691189 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7546. Min Act: -0.0003

Data Index: 636127 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7476. Min Act: -0.0003

Data Index: 222633 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7884. Min Act: -0.0003

Data Index: 1254536 (C4 (Web Text))

Max Activating Token Index: 55