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

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

Neuron 3374 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1013989 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4952. Min Act: -0.0000

Data Index: 265027 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1010375 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4397. Min Act: -0.0000

Data Index: 112387 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4246. Min Act: -0.0000

Data Index: 936528 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4174. Min Act: -0.0000

Data Index: 662729 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1179345 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4287. Min Act: -0.0000

Data Index: 492031 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4248. Min Act: -0.0000

Data Index: 649246 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4068. Min Act: -0.0000

Data Index: 660102 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1080891 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3992. Min Act: -0.0000

Data Index: 774057 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3901. Min Act: -0.0000

Data Index: 395093 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4068. Min Act: -0.0000

Data Index: 800507 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1115372 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3991. Min Act: -0.0000

Data Index: 902234 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1252679 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4070. Min Act: -0.0000

Data Index: 26871 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1086234 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4054. Min Act: -0.0000

Data Index: 544593 (C4 (Web Text))

Max Activating Token Index: 205