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

Dataset: The Pile

Neuron 1915 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0000

Data Index: 278058 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0345. Min Act: -0.0000

Data Index: 133582 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0346. Min Act: -0.0000

Data Index: 440014 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1784381 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0334. Min Act: -0.0000

Data Index: 410451 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1976027 (The Pile)

Max Activating Token Index: 997

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0331. Min Act: -0.0000

Data Index: 558716 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0329. Min Act: -0.0000

Data Index: 610282 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0330. Min Act: -0.0000

Data Index: 176275 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0328. Min Act: -0.0000

Data Index: 600966 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0327. Min Act: -0.0000

Data Index: 172333 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1135186 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0327. Min Act: -0.0000

Data Index: 30782 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1619634 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1625069 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1495691 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1427469 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0333. Min Act: -0.0000

Data Index: 877721 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0319. Min Act: -0.0001

Data Index: 493771 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1381057 (The Pile)

Max Activating Token Index: 971