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

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

Neuron 416 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4493. Min Act: -0.0000

Data Index: 1316704 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3868. Min Act: -0.0000

Data Index: 753516 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1284020 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1020113 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1239099 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4331. Min Act: -0.0000

Data Index: 900825 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4221. Min Act: -0.0000

Data Index: 834769 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1172225 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3082. Min Act: -0.0000

Data Index: 455273 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3002. Min Act: -0.0000

Data Index: 398321 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2849. Min Act: -0.0000

Data Index: 801951 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2805. Min Act: -0.0000

Data Index: 650163 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2769. Min Act: -0.0000

Data Index: 347907 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2948. Min Act: -0.0000

Data Index: 420347 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1072419 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.1987. Min Act: -0.0000

Data Index: 846487 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2293. Min Act: -0.0000

Data Index: 861303 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2081. Min Act: -0.0000

Data Index: 1194684 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2137. Min Act: -0.0000

Data Index: 275604 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1066118 (C4 (Web Text))

Max Activating Token Index: 107