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

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

Neuron 2317 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2038. Min Range: -2.2038

Max Act: 2.0380. Min Act: -0.0000

Data Index: 848629 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 2.2038. Min Range: -2.2038

Max Act: 2.1889. Min Act: -0.0000

Data Index: 443386 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 2.2038. Min Range: -2.2038

Max Act: 2.2038. Min Act: -0.0000

Data Index: 62821 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.9574. Min Act: -0.0000

Data Index: 1080186 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.9007. Min Act: -0.0000

Data Index: 278572 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.8885. Min Act: -0.0000

Data Index: 1149092 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.7374. Min Act: -0.0000

Data Index: 1078726 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.6777. Min Act: -0.0000

Data Index: 330391 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.7124. Min Act: -0.0000

Data Index: 1015851 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.6533. Min Act: -0.0000

Data Index: 856269 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.6374. Min Act: -0.0000

Data Index: 934985 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.6116. Min Act: -0.0000

Data Index: 312808 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5186. Min Act: -0.0000

Data Index: 701739 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1262694 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5854. Min Act: -0.0000

Data Index: 144858 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5704. Min Act: -0.0000

Data Index: 296331 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5695. Min Act: -0.0000

Data Index: 647360 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5659. Min Act: -0.0000

Data Index: 666322 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5390. Min Act: -0.0000

Data Index: 1195090 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 2.2038. Min Range: -2.2038

Max Act: 1.5152. Min Act: -0.0000

Data Index: 100160 (C4 (Web Text))

Max Activating Token Index: 122