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

Dataset: The Pile

Neuron 154 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.5695. Min Act: -0.0000

Data Index: 1668551 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.8503. Min Act: -0.0000

Data Index: 1056476 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4464. Min Act: -0.0000

Data Index: 1373742 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.6772. Min Act: -0.0000

Data Index: 1685037 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.6740. Min Act: -0.0000

Data Index: 216086 (The Pile)

Max Activating Token Index: 946

Text #5

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.7777. Min Act: -0.0000

Data Index: 493621 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.7465. Min Act: -0.0000

Data Index: 1052671 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.5154. Min Act: -0.0000

Data Index: 537709 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.6886. Min Act: -0.0000

Data Index: 533297 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.1906. Min Act: -0.0000

Data Index: 1892602 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.0410. Min Act: -0.0000

Data Index: 1520280 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.2279. Min Act: -0.0000

Data Index: 574243 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4088. Min Act: -0.0000

Data Index: 1135082 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.5405. Min Act: -0.0000

Data Index: 949258 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.1036. Min Act: -0.0000

Data Index: 1511404 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.3796. Min Act: -0.0000

Data Index: 1618426 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 3.9227. Min Range: -3.9227

Max Act: 2.4843. Min Act: -0.0000

Data Index: 949969 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.9227. Min Act: -0.0000

Data Index: 1251604 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4298. Min Act: -0.0000

Data Index: 1989130 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.0491. Min Act: -0.0000

Data Index: 611551 (The Pile)

Max Activating Token Index: 349