Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 819 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3173. Min Act: -0.0001

Data Index: 347728 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2987. Min Act: -0.0001

Data Index: 1206072 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2990. Min Act: -0.0001

Data Index: 790958 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2587. Min Act: -0.0001

Data Index: 1130953 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1352079 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2653. Min Act: -0.0001

Data Index: 697414 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2874. Min Act: -0.0001

Data Index: 86193 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2796. Min Act: -0.0001

Data Index: 235828 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1330544 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2660. Min Act: -0.0001

Data Index: 372525 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2510. Min Act: -0.0001

Data Index: 454234 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2518. Min Act: -0.0001

Data Index: 1120516 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2361. Min Act: -0.0001

Data Index: 274250 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2552. Min Act: -0.0001

Data Index: 111063 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1163813 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2453. Min Act: -0.0001

Data Index: 226440 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2597. Min Act: -0.0001

Data Index: 447076 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2319. Min Act: -0.0001

Data Index: 16822 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2313. Min Act: -0.0001

Data Index: 588883 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2249. Min Act: -0.0001

Data Index: 890617 (C4 (Web Text))

Max Activating Token Index: 385