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

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

Neuron 1351 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.9445. Min Act: -0.0000

Data Index: 192984 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.6416. Min Act: -0.0000

Data Index: 433085 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1086594 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.6180. Min Act: -0.0000

Data Index: 1003117 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1313805 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.5187. Min Act: -0.0000

Data Index: 914735 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.3029. Min Act: -0.0000

Data Index: 297324 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.5291. Min Act: -0.0000

Data Index: 463130 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.4969. Min Act: -0.0000

Data Index: 540538 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.2903. Min Act: -0.0000

Data Index: 939817 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.2288. Min Act: -0.0000

Data Index: 65669 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1004819 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.3230. Min Act: -0.0000

Data Index: 325517 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.2047. Min Act: -0.0000

Data Index: 965299 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1290054 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.1286. Min Act: -0.0000

Data Index: 196790 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.1470. Min Act: -0.0000

Data Index: 346399 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.1478. Min Act: -0.0000

Data Index: 318979 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.1016. Min Act: -0.0000

Data Index: 933795 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 1.9445. Min Range: -1.9445

Max Act: 1.0214. Min Act: -0.0000

Data Index: 699578 (C4 (Web Text))

Max Activating Token Index: 407