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

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

Neuron 4004 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8990. Min Range: -5.8990

Max Act: 5.8990. Min Act: -0.0000

Data Index: 243816 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 5.8990. Min Range: -5.8990

Max Act: 5.5894. Min Act: -0.0000

Data Index: 334877 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 5.8990. Min Range: -5.8990

Max Act: 5.7808. Min Act: -0.0000

Data Index: 905941 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 5.8990. Min Range: -5.8990

Max Act: 5.7969. Min Act: -0.0000

Data Index: 317847 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 5.8990. Min Range: -5.8990

Max Act: 5.4758. Min Act: -0.0000

Data Index: 293855 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.8891. Min Act: -0.0000

Data Index: 572851 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 5.8990. Min Range: -5.8990

Max Act: 5.2622. Min Act: -0.0000

Data Index: 444362 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.7713. Min Act: -0.0000

Data Index: 1334282 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 5.8990. Min Range: -5.8990

Max Act: 5.1200. Min Act: -0.0000

Data Index: 550218 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.6968. Min Act: -0.0000

Data Index: 1257119 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.6554. Min Act: -0.0000

Data Index: 514815 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.7931. Min Act: -0.0000

Data Index: 829223 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.5938. Min Act: -0.0000

Data Index: 1049873 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.9064. Min Act: -0.0000

Data Index: 298604 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.0423. Min Act: -0.0000

Data Index: 563865 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.5305. Min Act: -0.0000

Data Index: 854834 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 5.8990. Min Range: -5.8990

Max Act: 3.9923. Min Act: -0.0000

Data Index: 567414 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.6744. Min Act: -0.0000

Data Index: 1177003 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.2950. Min Act: -0.0000

Data Index: 363735 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 5.8990. Min Range: -5.8990

Max Act: 4.5942. Min Act: -0.0000

Data Index: 368424 (C4 (Web Text))

Max Activating Token Index: 654