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

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

Neuron 127 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.9487. Min Act: -0.0001

Data Index: 1297332 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.8477. Min Act: -0.0001

Data Index: 712233 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.8045. Min Act: -0.0001

Data Index: 302720 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.8469. Min Act: -0.0000

Data Index: 527526 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7277. Min Act: -0.0001

Data Index: 1214229 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7108. Min Act: -0.0001

Data Index: 1272889 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7009. Min Act: -0.0001

Data Index: 802152 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7085. Min Act: -0.0000

Data Index: 877471 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6779. Min Act: -0.0000

Data Index: 262846 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6522. Min Act: -0.0001

Data Index: 211006 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1035828 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6631. Min Act: -0.0001

Data Index: 492032 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1297221 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6199. Min Act: -0.0000

Data Index: 558362 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6493. Min Act: -0.0000

Data Index: 608991 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6438. Min Act: -0.0001

Data Index: 874887 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6294. Min Act: -0.0001

Data Index: 272120 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6337. Min Act: -0.0000

Data Index: 735504 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.5918. Min Act: -0.0000

Data Index: 191087 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6488. Min Act: -0.0000

Data Index: 405099 (C4 (Web Text))

Max Activating Token Index: 213