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

Dataset: The Pile

Neuron 2336 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2114. Min Range: -5.2114

Max Act: 5.2114. Min Act: -0.0000

Data Index: 763465 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.9553. Min Act: -0.0000

Data Index: 1962653 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.7658. Min Act: -0.0000

Data Index: 241675 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.8856. Min Act: -0.0000

Data Index: 1910756 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.6398. Min Act: -0.0000

Data Index: 1699056 (The Pile)

Max Activating Token Index: 57

Text #5

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.6102. Min Act: -0.0000

Data Index: 520477 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.5904. Min Act: -0.0000

Data Index: 1612661 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.5456. Min Act: -0.0000

Data Index: 1792589 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.7116. Min Act: -0.0000

Data Index: 1726715 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.4947. Min Act: -0.0000

Data Index: 1454386 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.4581. Min Act: -0.0000

Data Index: 1970498 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.4654. Min Act: -0.0000

Data Index: 673181 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.4383. Min Act: -0.0000

Data Index: 782634 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.2407. Min Act: 0.0000

Data Index: 1679156 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.4336. Min Act: -0.0000

Data Index: 1191010 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.2339. Min Act: -0.0000

Data Index: 935009 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.2205. Min Act: -0.0000

Data Index: 739136 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.3881. Min Act: -0.0000

Data Index: 1798356 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.3677. Min Act: -0.0000

Data Index: 1420821 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 5.2114. Min Range: -5.2114

Max Act: 4.1776. Min Act: -0.0000

Data Index: 520749 (The Pile)

Max Activating Token Index: 94