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

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

Neuron 3102 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1104540 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1274694 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4250. Min Act: -0.0000

Data Index: 468162 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4386. Min Act: -0.0000

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4025. Min Act: -0.0000

Data Index: 195894 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3983. Min Act: -0.0000

Data Index: 913609 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3611. Min Act: -0.0000

Data Index: 661309 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3456. Min Act: -0.0000

Data Index: 345132 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3431. Min Act: -0.0000

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3195. Min Act: -0.0000

Data Index: 889116 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3252. Min Act: -0.0000

Data Index: 189294 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3007. Min Act: -0.0000

Data Index: 806621 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3142. Min Act: -0.0000

Data Index: 252798 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3208. Min Act: -0.0000

Data Index: 864789 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3016. Min Act: -0.0000

Data Index: 319114 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.2839. Min Act: -0.0000

Data Index: 461170 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3035. Min Act: -0.0000

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.2882. Min Act: -0.0000

Data Index: 394038 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.2900. Min Act: -0.0000

Data Index: 727506 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.2745. Min Act: -0.0000

Data Index: 87016 (C4 (Web Text))

Max Activating Token Index: 537