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

Dataset: The Pile

Neuron 496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9073. Min Range: -5.9073

Max Act: 5.9073. Min Act: -0.0000

Data Index: 479637 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.9400. Min Act: -0.0000

Data Index: 370594 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 5.9073. Min Range: -5.9073

Max Act: 5.4988. Min Act: -0.0000

Data Index: 756419 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.8439. Min Act: -0.0000

Data Index: 217879 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.9195. Min Act: -0.0000

Data Index: 1968724 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.4587. Min Act: -0.0000

Data Index: 556705 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.1135. Min Act: -0.0000

Data Index: 1990289 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.3956. Min Act: -0.0000

Data Index: 1165299 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.2665. Min Act: -0.0000

Data Index: 1677268 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.3841. Min Act: -0.0000

Data Index: 1677715 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.6624. Min Act: -0.0000

Data Index: 316864 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.3967. Min Act: -0.0000

Data Index: 555477 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.3943. Min Act: -0.0000

Data Index: 551945 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 5.9073. Min Range: -5.9073

Max Act: 3.8230. Min Act: -0.0000

Data Index: 1709421 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 5.9073. Min Range: -5.9073

Max Act: 2.7681. Min Act: -0.0000

Data Index: 1985747 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.0707. Min Act: -0.0000

Data Index: 503966 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 5.9073. Min Range: -5.9073

Max Act: 3.7035. Min Act: -0.0000

Data Index: 822257 (The Pile)

Max Activating Token Index: 299

Text #17

Max Range: 5.9073. Min Range: -5.9073

Max Act: 3.8210. Min Act: -0.0000

Data Index: 1185582 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 5.9073. Min Range: -5.9073

Max Act: 3.7637. Min Act: -0.0000

Data Index: 857496 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 5.9073. Min Range: -5.9073

Max Act: 4.1582. Min Act: -0.0000

Data Index: 1206554 (The Pile)

Max Activating Token Index: 645