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

Dataset: The Pile

Neuron 692 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.5743. Min Act: -0.0000

Data Index: 1809236 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.4546. Min Act: -0.0000

Data Index: 1145407 (The Pile)

Max Activating Token Index: 182

Text #2

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.3085. Min Act: -0.0000

Data Index: 87807 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1849582 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.1819. Min Act: -0.0000

Data Index: 7892 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.1461. Min Act: -0.0000

Data Index: 419068 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1198949 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.1066. Min Act: -0.0000

Data Index: 689842 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.1527. Min Act: -0.0000

Data Index: 215059 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0236. Min Act: -0.0000

Data Index: 129819 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1624113 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1217727 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0635. Min Act: -0.0000

Data Index: 439669 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1248085 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0706. Min Act: -0.0000

Data Index: 369151 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0098. Min Act: -0.0000

Data Index: 540327 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 1.5743. Min Range: -1.5743

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1228332 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 1.5743. Min Range: -1.5743

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1433485 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 1.5743. Min Range: -1.5743

Max Act: 0.9572. Min Act: -0.0000

Data Index: 801830 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 1.5743. Min Range: -1.5743

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1590214 (The Pile)

Max Activating Token Index: 227