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

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

Neuron 2386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5536. Min Act: -0.0000

Data Index: 233200 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4813. Min Act: -0.0001

Data Index: 1082160 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4903. Min Act: -0.0001

Data Index: 311584 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4511. Min Act: -0.0000

Data Index: 803081 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4561. Min Act: -0.0000

Data Index: 82125 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4531. Min Act: -0.0001

Data Index: 108875 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4590. Min Act: -0.0000

Data Index: 877084 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4404. Min Act: -0.0000

Data Index: 287636 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1185278 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1186088 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4280. Min Act: -0.0000

Data Index: 103482 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1076324 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4596. Min Act: -0.0000

Data Index: 812020 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4302. Min Act: -0.0000

Data Index: 851486 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4237. Min Act: -0.0001

Data Index: 266496 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4371. Min Act: -0.0000

Data Index: 771073 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4244. Min Act: -0.0001

Data Index: 140638 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4363. Min Act: -0.0001

Data Index: 1096396 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1260772 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4173. Min Act: -0.0001

Data Index: 684350 (C4 (Web Text))

Max Activating Token Index: 894