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

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

Neuron 1408 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.9560. Min Act: -0.0001

Data Index: 345413 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8110. Min Act: -0.0001

Data Index: 99553 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8110. Min Act: -0.0001

Data Index: 761315 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7708. Min Act: -0.0001

Data Index: 500748 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7667. Min Act: -0.0001

Data Index: 1067972 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7232. Min Act: -0.0001

Data Index: 644609 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6564. Min Act: -0.0001

Data Index: 808208 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7271. Min Act: -0.0001

Data Index: 748644 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6689. Min Act: -0.0001

Data Index: 90949 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.5778. Min Act: -0.0001

Data Index: 12143 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6597. Min Act: -0.0001

Data Index: 335536 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6789. Min Act: -0.0001

Data Index: 450567 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6508. Min Act: -0.0001

Data Index: 550255 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6314. Min Act: -0.0001

Data Index: 577401 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6374. Min Act: -0.0001

Data Index: 65026 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6273. Min Act: -0.0001

Data Index: 621728 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6196. Min Act: -0.0001

Data Index: 840399 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6216. Min Act: -0.0001

Data Index: 958650 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6173. Min Act: -0.0001

Data Index: 684546 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.6156. Min Act: -0.0001

Data Index: 1063762 (C4 (Web Text))

Max Activating Token Index: 101