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

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

Neuron 4321 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1823. Min Range: -1.1823

Max Act: 1.1823. Min Act: -0.0000

Data Index: 432706 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.9191. Min Act: -0.0000

Data Index: 875396 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8583. Min Act: -0.0000

Data Index: 837430 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8842. Min Act: -0.0000

Data Index: 909735 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8467. Min Act: -0.0000

Data Index: 721534 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1116115 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1183964 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1347756 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8174. Min Act: -0.0000

Data Index: 494099 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8037. Min Act: -0.0000

Data Index: 832878 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8338. Min Act: -0.0000

Data Index: 310416 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.8000. Min Act: -0.0000

Data Index: 542099 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7941. Min Act: -0.0000

Data Index: 718368 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7761. Min Act: -0.0000

Data Index: 302592 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7607. Min Act: -0.0000

Data Index: 738477 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7593. Min Act: -0.0000

Data Index: 651950 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7972. Min Act: -0.0000

Data Index: 205130 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7440. Min Act: -0.0000

Data Index: 655682 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7178. Min Act: -0.0000

Data Index: 550265 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.1823. Min Range: -1.1823

Max Act: 0.7443. Min Act: -0.0000

Data Index: 3286 (C4 (Web Text))

Max Activating Token Index: 274