Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3204 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3293. Min Range: -2.3293

Max Act: 2.3293. Min Act: -0.0000

Data Index: 845199 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.9442. Min Act: -0.0000

Data Index: 994579 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.9062. Min Act: -0.0000

Data Index: 743246 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1328582 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.7223. Min Act: -0.0000

Data Index: 933161 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.7246. Min Act: -0.0000

Data Index: 1231618 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.6066. Min Act: -0.0000

Data Index: 658822 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.5735. Min Act: -0.0000

Data Index: 1348634 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1262030 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.5081. Min Act: -0.0000

Data Index: 92431 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.5113. Min Act: -0.0000

Data Index: 362148 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.5041. Min Act: -0.0000

Data Index: 75851 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.4790. Min Act: -0.0000

Data Index: 303076 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.4833. Min Act: -0.0000

Data Index: 1027661 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.4830. Min Act: -0.0000

Data Index: 712744 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.4571. Min Act: -0.0000

Data Index: 1290413 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.5385. Min Act: -0.0000

Data Index: 186047 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.4361. Min Act: -0.0000

Data Index: 898499 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.4431. Min Act: -0.0000

Data Index: 704915 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 2.3293. Min Range: -2.3293

Max Act: 1.4325. Min Act: -0.0000

Data Index: 932592 (C4 (Web Text))

Max Activating Token Index: 467