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

Dataset: The Pile

Neuron 456 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.8005. Min Act: -0.0000

Data Index: 841823 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.6334. Min Act: -0.0000

Data Index: 962587 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.5520. Min Act: -0.0000

Data Index: 731871 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.6837. Min Act: -0.0001

Data Index: 1580802 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.5408. Min Act: -0.0000

Data Index: 429539 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.4382. Min Act: -0.0000

Data Index: 1237441 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.5453. Min Act: -0.0000

Data Index: 814377 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.4683. Min Act: -0.0000

Data Index: 362978 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.3941. Min Act: -0.0000

Data Index: 667048 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.4243. Min Act: -0.0000

Data Index: 1710457 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1165189 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.4204. Min Act: -0.0000

Data Index: 296048 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.3537. Min Act: -0.0000

Data Index: 44422 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.2742. Min Act: -0.0000

Data Index: 595883 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.3817. Min Act: -0.0000

Data Index: 772200 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.2589. Min Act: -0.0000

Data Index: 750018 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.2861. Min Act: -0.0000

Data Index: 1392761 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.3163. Min Act: -0.0001

Data Index: 36880 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1882771 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 1.8005. Min Range: -1.8005

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1907898 (The Pile)

Max Activating Token Index: 289