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

Dataset: The Pile

Neuron 41 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1192281 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2657. Min Act: 0.0000

Data Index: 1186733 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2944. Min Act: -0.0000

Data Index: 152813 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1819821 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1468957 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1997993 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1234607 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2146. Min Act: -0.0000

Data Index: 739387 (The Pile)

Max Activating Token Index: 184

Text #8

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1244. Min Act: -0.0000

Data Index: 553278 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1842. Min Act: -0.0000

Data Index: 17657 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1339. Min Act: -0.0000

Data Index: 871996 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.1354. Min Act: -0.0000

Data Index: 771287 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.0628. Min Act: -0.0000

Data Index: 419134 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 1.4587. Min Range: -1.4587

Max Act: 0.9885. Min Act: -0.0000

Data Index: 293933 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.4587. Min Range: -1.4587

Max Act: 0.9465. Min Act: -0.0000

Data Index: 973048 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.0188. Min Act: -0.0000

Data Index: 1361718 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1274827 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1980186 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1106274 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1705860 (The Pile)

Max Activating Token Index: 816