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

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

Neuron 2829 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2920. Min Range: -3.2920

Max Act: 3.2920. Min Act: -0.0000

Data Index: 1033620 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.9437. Min Act: -0.0000

Data Index: 1163701 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.7994. Min Act: -0.0000

Data Index: 51926 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.7333. Min Act: -0.0000

Data Index: 836547 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.7121. Min Act: -0.0000

Data Index: 195775 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.6939. Min Act: -0.0000

Data Index: 1333884 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.6186. Min Act: -0.0000

Data Index: 932777 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.5702. Min Act: -0.0000

Data Index: 135687 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.8404. Min Act: -0.0000

Data Index: 767202 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.4025. Min Act: -0.0000

Data Index: 301026 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.5222. Min Act: -0.0000

Data Index: 1289485 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.5244. Min Act: -0.0000

Data Index: 782452 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.3798. Min Act: -0.0000

Data Index: 729693 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.4805. Min Act: -0.0000

Data Index: 889933 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.4530. Min Act: -0.0000

Data Index: 1249313 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.5647. Min Act: -0.0000

Data Index: 508746 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.4320. Min Act: -0.0000

Data Index: 1231942 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.2867. Min Act: -0.0000

Data Index: 602350 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.2674. Min Act: -0.0000

Data Index: 1305920 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 3.2920. Min Range: -3.2920

Max Act: 2.3661. Min Act: -0.0000

Data Index: 8453 (C4 (Web Text))

Max Activating Token Index: 849