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

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

Neuron 3731 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4686. Min Act: -0.0002

Data Index: 857353 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1265225 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4842. Min Act: -0.0002

Data Index: 120884 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4528. Min Act: -0.0002

Data Index: 1274534 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4265. Min Act: -0.0001

Data Index: 697205 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4264. Min Act: -0.0002

Data Index: 193682 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4009. Min Act: -0.0002

Data Index: 186805 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3926. Min Act: -0.0002

Data Index: 41501 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4173. Min Act: -0.0002

Data Index: 690592 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4177. Min Act: -0.0002

Data Index: 826158 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4288. Min Act: -0.0002

Data Index: 119614 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4017. Min Act: -0.0002

Data Index: 658627 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4128. Min Act: -0.0001

Data Index: 1169289 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4009. Min Act: -0.0002

Data Index: 1115905 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4101. Min Act: -0.0001

Data Index: 728203 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3954. Min Act: -0.0002

Data Index: 1175990 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3910. Min Act: -0.0001

Data Index: 220091 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3639. Min Act: -0.0002

Data Index: 1165061 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3921. Min Act: -0.0002

Data Index: 741623 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4153. Min Act: -0.0002

Data Index: 1185148 (C4 (Web Text))

Max Activating Token Index: 540