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

Dataset: The Pile

Neuron 3207 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: 1.9230. Min Range: -1.9230

Max Act: 1.9230. Min Act: -0.0000

Data Index: 1285385 (The Pile)

Max Activating Token Index: 409

Text #1

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.7862. Min Act: -0.0000

Data Index: 365963 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.6329. Min Act: -0.0001

Data Index: 1988138 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.4309. Min Act: -0.0000

Data Index: 526828 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.6374. Min Act: -0.0000

Data Index: 1115968 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.3707. Min Act: -0.0000

Data Index: 86081 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1092129 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.3204. Min Act: -0.0001

Data Index: 1184079 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1433544 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1259467 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1138282 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.3405. Min Act: -0.0000

Data Index: 802969 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1385926 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1601226 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.3659. Min Act: -0.0000

Data Index: 1051863 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.3612. Min Act: -0.0000

Data Index: 1054715 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.1481. Min Act: -0.0000

Data Index: 659858 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.1955. Min Act: -0.0000

Data Index: 240548 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1400175 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 1.9230. Min Range: -1.9230

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1678985 (The Pile)

Max Activating Token Index: 191