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

Dataset: The Pile

Neuron 2345 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1694837 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3982. Min Act: -0.0000

Data Index: 784900 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1270506 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1323030 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3376. Min Act: -0.0000

Data Index: 119397 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3286. Min Act: -0.0000

Data Index: 709882 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1880126 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3044. Min Act: -0.0000

Data Index: 744160 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1757951 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3373. Min Act: -0.0000

Data Index: 490373 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1091264 (The Pile)

Max Activating Token Index: 923

Text #11

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1433062 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3094. Min Act: -0.0000

Data Index: 167688 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1151123 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1987024 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1055997 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3043. Min Act: -0.0000

Data Index: 734419 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1885850 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2799. Min Act: -0.0000

Data Index: 625515 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3008. Min Act: -0.0000

Data Index: 311281 (The Pile)

Max Activating Token Index: 48