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

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

Neuron 2817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4869. Min Act: -0.0000

Data Index: 904223 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4876. Min Act: -0.0000

Data Index: 698336 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4982. Min Act: -0.0000

Data Index: 556139 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4298. Min Act: -0.0000

Data Index: 847141 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4488. Min Act: -0.0000

Data Index: 922034 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3971. Min Act: -0.0001

Data Index: 1111887 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3891. Min Act: -0.0000

Data Index: 878326 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3899. Min Act: -0.0001

Data Index: 657232 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3946. Min Act: -0.0000

Data Index: 892311 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1138515 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3768. Min Act: -0.0000

Data Index: 906848 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1355122 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3877. Min Act: -0.0000

Data Index: 538415 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1230579 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3365. Min Act: -0.0001

Data Index: 681390 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3800. Min Act: -0.0000

Data Index: 988516 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4153. Min Act: -0.0000

Data Index: 645445 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3295. Min Act: -0.0000

Data Index: 637194 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3744. Min Act: -0.0001

Data Index: 262626 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3631. Min Act: -0.0000

Data Index: 609389 (C4 (Web Text))

Max Activating Token Index: 1002