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

Dataset: The Pile

Neuron 3877 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2916. Min Act: 0.0000

Data Index: 190907 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2574. Min Act: 0.0000

Data Index: 1847186 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2755. Min Act: -0.0000

Data Index: 319529 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1891211 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2241. Min Act: -0.0000

Data Index: 956580 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2506. Min Act: -0.0000

Data Index: 408767 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1064268 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2463. Min Act: 0.0000

Data Index: 1254381 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2401. Min Act: -0.0000

Data Index: 129229 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2361. Min Act: -0.0000

Data Index: 765793 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1998550 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2404. Min Act: -0.0000

Data Index: 998511 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2414. Min Act: 0.0000

Data Index: 1843062 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2437. Min Act: -0.0000

Data Index: 652911 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2339. Min Act: -0.0000

Data Index: 900433 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1648823 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2261. Min Act: -0.0000

Data Index: 304595 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1270432 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1128906 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2290. Min Act: 0.0000

Data Index: 1689788 (The Pile)

Max Activating Token Index: 110