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

Dataset: The Pile

Neuron 3743 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: 0.4277. Min Range: -0.4277

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1430161 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1314545 (The Pile)

Max Activating Token Index: 932

Text #2

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3729. Min Act: -0.0000

Data Index: 407605 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3756. Min Act: 0.0000

Data Index: 1326169 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3610. Min Act: 0.0000

Data Index: 295923 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3457. Min Act: -0.0000

Data Index: 839008 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1449310 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3420. Min Act: -0.0000

Data Index: 39703 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3413. Min Act: -0.0000

Data Index: 547259 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1905780 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3241. Min Act: -0.0000

Data Index: 483625 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1726469 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1215480 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1533751 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3228. Min Act: -0.0000

Data Index: 209935 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3437. Min Act: -0.0000

Data Index: 3409 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1399749 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1459329 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2277. Min Act: -0.0000

Data Index: 126892 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3363. Min Act: -0.0000

Data Index: 746779 (The Pile)

Max Activating Token Index: 284