Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 67 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.2480. Min Range: -5.2480

Max Act: 5.2480. Min Act: -0.0001

Data Index: 943209 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.9107. Min Act: -0.0001

Data Index: 1313106 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.7357. Min Act: -0.0001

Data Index: 887309 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.2527. Min Act: -0.0001

Data Index: 1042008 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.3789. Min Act: -0.0001

Data Index: 886288 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.2131. Min Act: -0.0001

Data Index: 1277825 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.9887. Min Act: -0.0001

Data Index: 90751 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.8653. Min Act: -0.0001

Data Index: 562361 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.2243. Min Act: -0.0001

Data Index: 395173 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.0467. Min Act: -0.0001

Data Index: 786932 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.8716. Min Act: -0.0001

Data Index: 549733 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 5.2480. Min Range: -5.2480

Max Act: 4.0065. Min Act: -0.0001

Data Index: 774509 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.8402. Min Act: -0.0001

Data Index: 1350975 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.8496. Min Act: -0.0001

Data Index: 915029 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.9951. Min Act: -0.0001

Data Index: 1256502 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.9780. Min Act: -0.0001

Data Index: 487819 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.9645. Min Act: -0.0001

Data Index: 722059 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.8127. Min Act: -0.0001

Data Index: 596651 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.9376. Min Act: -0.0001

Data Index: 1301059 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 5.2480. Min Range: -5.2480

Max Act: 3.7865. Min Act: -0.0001

Data Index: 883035 (C4 (Web Text))

Max Activating Token Index: 736