Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2247 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4931. Min Act: -0.0001

Data Index: 31883 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4792. Min Act: -0.0001

Data Index: 376917 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4456. Min Act: -0.0001

Data Index: 849278 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4192. Min Act: -0.0001

Data Index: 295903 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4156. Min Act: -0.0001

Data Index: 283499 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4482. Min Act: -0.0001

Data Index: 547763 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4184. Min Act: -0.0001

Data Index: 50296 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4420. Min Act: -0.0001

Data Index: 1140709 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3983. Min Act: -0.0001

Data Index: 348855 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4464. Min Act: -0.0001

Data Index: 620581 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4170. Min Act: -0.0001

Data Index: 373862 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3921. Min Act: -0.0001

Data Index: 1028299 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4380. Min Act: -0.0001

Data Index: 491572 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3853. Min Act: -0.0001

Data Index: 517568 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3883. Min Act: -0.0001

Data Index: 398790 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3709. Min Act: -0.0001

Data Index: 820905 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4051. Min Act: -0.0001

Data Index: 732814 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4008. Min Act: -0.0001

Data Index: 212109 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1149972 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3855. Min Act: -0.0001

Data Index: 854355 (C4 (Web Text))

Max Activating Token Index: 873