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

Dataset: The Pile

Neuron 1240 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1233399 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1521534 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1682800 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4207. Min Act: -0.0000

Data Index: 135767 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1602462 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3965. Min Act: -0.0000

Data Index: 886706 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4187. Min Act: -0.0000

Data Index: 654705 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1531910 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1721739 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3692. Min Act: -0.0000

Data Index: 745478 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1403476 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1124905 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1222533 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3453. Min Act: -0.0000

Data Index: 701206 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3472. Min Act: -0.0000

Data Index: 261298 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3409. Min Act: -0.0000

Data Index: 964421 (The Pile)

Max Activating Token Index: 220

Text #16

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3396. Min Act: -0.0000

Data Index: 808495 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1216985 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3400. Min Act: -0.0000

Data Index: 361292 (The Pile)

Max Activating Token Index: 525

Text #19

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3619. Min Act: -0.0000

Data Index: 953802 (The Pile)

Max Activating Token Index: 292