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

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

Neuron 3784 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.4267. Min Act: -0.0000

Data Index: 837259 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1063247 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3783. Min Act: -0.0000

Data Index: 415444 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1125278 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3992. Min Act: -0.0000

Data Index: 360852 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3770. Min Act: -0.0000

Data Index: 616822 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3799. Min Act: -0.0000

Data Index: 35210 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3313. Min Act: -0.0000

Data Index: 580198 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3433. Min Act: -0.0000

Data Index: 32694 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3567. Min Act: -0.0000

Data Index: 909685 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3180. Min Act: -0.0000

Data Index: 623997 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3166. Min Act: -0.0000

Data Index: 892126 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1271507 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2772. Min Act: -0.0000

Data Index: 886048 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3214. Min Act: -0.0000

Data Index: 358615 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1326697 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2823. Min Act: -0.0000

Data Index: 31447 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2784. Min Act: -0.0000

Data Index: 994265 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1106475 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2621. Min Act: -0.0000

Data Index: 871117 (C4 (Web Text))

Max Activating Token Index: 486