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

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

Neuron 1063 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: 2.7809. Min Range: -2.7809

Max Act: 2.7809. Min Act: -0.0000

Data Index: 216924 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.4791. Min Act: -0.0000

Data Index: 670668 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.9421. Min Act: -0.0000

Data Index: 281575 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.0440. Min Act: -0.0000

Data Index: 1230883 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7759. Min Act: -0.0000

Data Index: 545357 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.9787. Min Act: -0.0000

Data Index: 799938 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7091. Min Act: -0.0000

Data Index: 130887 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.8033. Min Act: -0.0000

Data Index: 1242563 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7932. Min Act: -0.0000

Data Index: 818606 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7833. Min Act: -0.0000

Data Index: 25779 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1322579 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.4967. Min Act: -0.0000

Data Index: 3282 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.9810. Min Act: -0.0000

Data Index: 338912 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.8757. Min Act: -0.0000

Data Index: 313433 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7433. Min Act: -0.0000

Data Index: 527337 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.9180. Min Act: -0.0000

Data Index: 1206378 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.6238. Min Act: -0.0000

Data Index: 210361 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7956. Min Act: -0.0000

Data Index: 568016 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1078485 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 2.7809. Min Range: -2.7809

Max Act: 1.7057. Min Act: -0.0000

Data Index: 916392 (C4 (Web Text))

Max Activating Token Index: 86