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

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

Neuron 308 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1222. Min Act: -0.0000

Data Index: 516522 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1272756 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1067. Min Act: -0.0001

Data Index: 209300 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0801. Min Act: -0.0000

Data Index: 826489 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0853. Min Act: -0.0000

Data Index: 409950 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0857. Min Act: -0.0000

Data Index: 654102 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1470721 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0870. Min Act: -0.0001

Data Index: 66812 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0686. Min Act: -0.0001

Data Index: 917054 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0736. Min Act: 0.0000

Data Index: 75328 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0811. Min Act: 0.0001

Data Index: 552220 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0739. Min Act: 0.0000

Data Index: 779110 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0689. Min Act: 0.0000

Data Index: 1617256 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0764. Min Act: 0.0001

Data Index: 180664 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0717. Min Act: -0.0001

Data Index: 278327 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0731. Min Act: -0.0000

Data Index: 644320 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0641. Min Act: -0.0000

Data Index: 627828 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0607. Min Act: -0.0001

Data Index: 994482 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0784. Min Act: 0.0000

Data Index: 116288 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0628. Min Act: -0.0001

Data Index: 385835 (C4 (Web Text))

Max Activating Token Index: 377