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

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

Neuron 2592 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.9618. Min Act: -0.0001

Data Index: 341937 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7834. Min Act: -0.0002

Data Index: 21479 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1179228 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7753. Min Act: -0.0001

Data Index: 1291444 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7579. Min Act: -0.0001

Data Index: 673189 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6465. Min Act: -0.0001

Data Index: 117250 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7117. Min Act: -0.0001

Data Index: 531645 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6634. Min Act: -0.0002

Data Index: 162972 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8444. Min Act: -0.0002

Data Index: 914013 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7910. Min Act: -0.0001

Data Index: 212270 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7306. Min Act: -0.0002

Data Index: 1199851 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7118. Min Act: -0.0001

Data Index: 115269 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6617. Min Act: -0.0001

Data Index: 786588 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7179. Min Act: -0.0002

Data Index: 33643 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6790. Min Act: -0.0001

Data Index: 747968 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6449. Min Act: -0.0002

Data Index: 794050 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6903. Min Act: -0.0001

Data Index: 513217 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7118. Min Act: -0.0001

Data Index: 213231 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7103. Min Act: -0.0001

Data Index: 409211 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.6554. Min Act: -0.0001

Data Index: 259063 (C4 (Web Text))

Max Activating Token Index: 558