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

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

Neuron 1702 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.8052. Min Act: -0.0001

Data Index: 801441 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.0689. Min Range: -1.0689

Max Act: 1.0689. Min Act: -0.0001

Data Index: 399655 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.8759. Min Act: -0.0001

Data Index: 1048981 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.9334. Min Act: -0.0001

Data Index: 786278 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.9750. Min Act: -0.0001

Data Index: 1327117 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.8542. Min Act: -0.0001

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1320971 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.8384. Min Act: -0.0001

Data Index: 803741 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.9579. Min Act: -0.0001

Data Index: 739315 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7994. Min Act: -0.0001

Data Index: 351622 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7830. Min Act: -0.0001

Data Index: 436299 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7710. Min Act: -0.0001

Data Index: 254803 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.8359. Min Act: -0.0001

Data Index: 782373 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7642. Min Act: -0.0001

Data Index: 497511 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7318. Min Act: -0.0001

Data Index: 98534 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.6917. Min Act: -0.0001

Data Index: 282 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7201. Min Act: -0.0001

Data Index: 626045 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7302. Min Act: -0.0001

Data Index: 651416 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7278. Min Act: -0.0001

Data Index: 362402 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.0689. Min Range: -1.0689

Max Act: 0.7026. Min Act: -0.0001

Data Index: 195709 (C4 (Web Text))

Max Activating Token Index: 949