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

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

Neuron 1310 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.5842. Min Act: -0.0001

Data Index: 178228 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.5898. Min Act: -0.0001

Data Index: 720467 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.4872. Min Act: -0.0001

Data Index: 917862 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.4930. Min Act: -0.0001

Data Index: 861293 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.3984. Min Act: -0.0001

Data Index: 536551 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.2961. Min Act: -0.0001

Data Index: 1100190 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.2763. Min Act: -0.0001

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.3170. Min Act: -0.0001

Data Index: 1103004 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.4408. Min Act: -0.0001

Data Index: 799155 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.3056. Min Act: -0.0001

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.3049. Min Act: -0.0001

Data Index: 147378 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.1144. Min Act: -0.0001

Data Index: 845342 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.1953. Min Act: -0.0001

Data Index: 182614 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.2889. Min Act: -0.0001

Data Index: 1100436 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.1732. Min Act: -0.0001

Data Index: 560158 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.2886. Min Act: -0.0001

Data Index: 667419 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.1929. Min Act: -0.0001

Data Index: 278334 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.1464. Min Act: -0.0001

Data Index: 84639 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.1470. Min Act: -0.0001

Data Index: 1173320 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 1.5898. Min Range: -1.5898

Max Act: 1.1854. Min Act: -0.0001

Data Index: 964274 (C4 (Web Text))

Max Activating Token Index: 1002