Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 71 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3642. Min Act: -0.0001

Data Index: 904146 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1311995 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2785. Min Act: -0.0001

Data Index: 390993 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2713. Min Act: -0.0001

Data Index: 104778 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2485. Min Act: -0.0001

Data Index: 853657 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1147472 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2533. Min Act: -0.0001

Data Index: 750554 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2913. Min Act: -0.0001

Data Index: 1227769 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2408. Min Act: -0.0001

Data Index: 684428 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2568. Min Act: -0.0001

Data Index: 339352 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2513. Min Act: -0.0001

Data Index: 372553 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2522. Min Act: -0.0001

Data Index: 583883 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2413. Min Act: -0.0001

Data Index: 513852 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2128. Min Act: -0.0001

Data Index: 247175 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1067623 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2415. Min Act: -0.0001

Data Index: 1033734 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2235. Min Act: -0.0001

Data Index: 772014 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2183. Min Act: -0.0001

Data Index: 284003 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1103318 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2164. Min Act: -0.0001

Data Index: 530978 (C4 (Web Text))

Max Activating Token Index: 337