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

Dataset: The Pile

Neuron 2186 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: 0.3936. Min Range: -0.3936

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1398513 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1144945 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3835. Min Act: -0.0000

Data Index: 352217 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1977039 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1432273 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3459. Min Act: -0.0000

Data Index: 748858 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3238. Min Act: -0.0000

Data Index: 631924 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3275. Min Act: -0.0000

Data Index: 32746 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3055. Min Act: -0.0000

Data Index: 617842 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3106. Min Act: -0.0000

Data Index: 642310 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3379. Min Act: -0.0000

Data Index: 744540 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1649084 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2780. Min Act: -0.0000

Data Index: 821887 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2553. Min Act: -0.0000

Data Index: 101278 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1927882 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2935. Min Act: -0.0000

Data Index: 632435 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2860. Min Act: -0.0000

Data Index: 93683 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1297726 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2646. Min Act: -0.0000

Data Index: 547953 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1372066 (The Pile)

Max Activating Token Index: 495