Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2119 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.4688. Min Act: -0.0000

Data Index: 607947 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.2762. Min Act: -0.0000

Data Index: 989194 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.4175. Min Act: -0.0000

Data Index: 405126 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.4472. Min Act: -0.0000

Data Index: 871353 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.2602. Min Act: -0.0000

Data Index: 14312 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.2035. Min Act: -0.0000

Data Index: 295274 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.4708. Min Act: -0.0000

Data Index: 969660 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.2824. Min Act: -0.0000

Data Index: 10781 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.3557. Min Act: -0.0000

Data Index: 862567 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.1943. Min Act: -0.0000

Data Index: 663954 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1550398 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1318767 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.2000. Min Act: -0.0000

Data Index: 61675 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1281626 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.1845. Min Act: -0.0000

Data Index: 198634 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1018516 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.1937. Min Act: -0.0000

Data Index: 575975 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.1191. Min Act: -0.0000

Data Index: 72419 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.0290. Min Act: -0.0000

Data Index: 688686 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.4708. Min Range: -1.4708

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1632759 (Python Code)

Max Activating Token Index: 35