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

Dataset: The Pile

Neuron 4190 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: 0.8127. Min Range: -0.8127

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1637538 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7532. Min Act: -0.0000

Data Index: 268023 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1612963 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1449924 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7510. Min Act: -0.0000

Data Index: 57003 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1182833 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6822. Min Act: -0.0000

Data Index: 866369 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6856. Min Act: -0.0000

Data Index: 343407 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.5983. Min Act: -0.0000

Data Index: 120256 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1625906 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1687330 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1398921 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6564. Min Act: -0.0000

Data Index: 932453 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6695. Min Act: -0.0000

Data Index: 836811 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6353. Min Act: -0.0000

Data Index: 63858 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6915. Min Act: -0.0000

Data Index: 326569 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1815858 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1098707 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1266896 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1563760 (The Pile)

Max Activating Token Index: 64