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

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

Neuron 2428 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: 0.7645. Min Range: -0.7645

Max Act: 0.7645. Min Act: -0.0002

Data Index: 1090653 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5542. Min Act: -0.0001

Data Index: 268005 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5460. Min Act: -0.0002

Data Index: 1128467 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5305. Min Act: -0.0002

Data Index: 595530 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5473. Min Act: -0.0001

Data Index: 514563 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5592. Min Act: -0.0002

Data Index: 1020982 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4865. Min Act: -0.0001

Data Index: 656492 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4676. Min Act: -0.0002

Data Index: 98546 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5128. Min Act: -0.0002

Data Index: 737848 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4667. Min Act: -0.0001

Data Index: 1050049 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5041. Min Act: -0.0002

Data Index: 1235066 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4732. Min Act: -0.0002

Data Index: 518466 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4818. Min Act: -0.0002

Data Index: 1242466 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5051. Min Act: -0.0002

Data Index: 671126 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4482. Min Act: -0.0001

Data Index: 790949 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4756. Min Act: -0.0001

Data Index: 51505 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4041. Min Act: -0.0002

Data Index: 553380 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4725. Min Act: -0.0002

Data Index: 198987 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4101. Min Act: -0.0002

Data Index: 35779 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4453. Min Act: -0.0002

Data Index: 992384 (C4 (Web Text))

Max Activating Token Index: 518