Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2389 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.4919. Min Range: -8.4919

Max Act: 8.4919. Min Act: -0.0000

Data Index: 1191553 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 8.4919. Min Range: -8.4919

Max Act: 7.9151. Min Act: -0.0000

Data Index: 157024 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 8.4919. Min Range: -8.4919

Max Act: 7.2698. Min Act: -0.0000

Data Index: 625711 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.8290. Min Act: -0.0000

Data Index: 1232450 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 8.4919. Min Range: -8.4919

Max Act: 7.5105. Min Act: -0.0000

Data Index: 255373 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 8.4919. Min Range: -8.4919

Max Act: 7.2694. Min Act: -0.0000

Data Index: 1176789 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.8443. Min Act: -0.0000

Data Index: 301833 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 8.4919. Min Range: -8.4919

Max Act: 7.0153. Min Act: -0.0000

Data Index: 968644 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 8.4919. Min Range: -8.4919

Max Act: 7.0157. Min Act: -0.0000

Data Index: 760892 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.2213. Min Act: -0.0000

Data Index: 400232 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.5485. Min Act: -0.0000

Data Index: 1035363 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.2821. Min Act: -0.0000

Data Index: 175667 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.0299. Min Act: -0.0000

Data Index: 399150 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.6445. Min Act: -0.0000

Data Index: 1160211 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.9989. Min Act: -0.0000

Data Index: 1305603 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.1841. Min Act: -0.0000

Data Index: 1170333 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.4886. Min Act: -0.0000

Data Index: 610856 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.2338. Min Act: -0.0001

Data Index: 525779 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 8.4919. Min Range: -8.4919

Max Act: 5.9954. Min Act: -0.0000

Data Index: 586415 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 8.4919. Min Range: -8.4919

Max Act: 6.0928. Min Act: -0.0000

Data Index: 1334990 (C4 (Web Text))

Max Activating Token Index: 163