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

Dataset: The Pile

Neuron 2336 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: 1.2658. Min Range: -1.2658

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1870842 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1333370 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.2384. Min Act: -0.0000

Data Index: 511686 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1402. Min Act: -0.0000

Data Index: 771801 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1534729 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1344903 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1459516 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1023878 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.2658. Min Range: -1.2658

Max Act: 0.9772. Min Act: -0.0000

Data Index: 1524077 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1418650 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0771. Min Act: -0.0000

Data Index: 709353 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.2043. Min Act: -0.0000

Data Index: 386030 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1520767 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0791. Min Act: -0.0000

Data Index: 1363845 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0304. Min Act: -0.0000

Data Index: 186431 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.2658. Min Range: -1.2658

Max Act: 0.9725. Min Act: 0.0000

Data Index: 1864503 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1186860 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1458399 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0110. Min Act: -0.0000

Data Index: 205615 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1661565 (The Pile)

Max Activating Token Index: 103