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

Dataset: The Pile

Neuron 238 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3852. Min Act: -0.0000

Data Index: 149577 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3656. Min Act: -0.0000

Data Index: 79641 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3171. Min Act: -0.0000

Data Index: 538490 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1579716 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2511. Min Act: -0.0000

Data Index: 148380 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2441. Min Act: -0.0000

Data Index: 250033 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1735457 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2352. Min Act: -0.0000

Data Index: 131547 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2300. Min Act: -0.0000

Data Index: 507662 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2302. Min Act: -0.0000

Data Index: 142050 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1533846 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2253. Min Act: -0.0000

Data Index: 24295 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1427872 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1934431 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2325. Min Act: -0.0000

Data Index: 764283 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1183418 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1533751 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2017. Min Act: -0.0000

Data Index: 719568 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2145. Min Act: -0.0000

Data Index: 286990 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1011827 (The Pile)

Max Activating Token Index: 820