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

Dataset: The Pile

Neuron 3474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3477. Min Act: -0.0000

Data Index: 359827 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1004655 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1583689 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3103. Min Act: -0.0000

Data Index: 358227 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3166. Min Act: -0.0000

Data Index: 987869 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3251. Min Act: -0.0000

Data Index: 590875 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1914216 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3204. Min Act: -0.0000

Data Index: 783394 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1102791 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3192. Min Act: -0.0000

Data Index: 973323 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1621565 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2977. Min Act: -0.0000

Data Index: 542752 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1876950 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1268007 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3123. Min Act: -0.0000

Data Index: 700741 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1444834 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1953991 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2884. Min Act: -0.0000

Data Index: 914406 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1992536 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2925. Min Act: -0.0000

Data Index: 506078 (The Pile)

Max Activating Token Index: 628