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

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

Neuron 940 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.5645. Min Act: -0.0000

Data Index: 66852 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.5445. Min Act: 0.0000

Data Index: 742400 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1189478 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.5303. Min Act: 0.0001

Data Index: 1192126 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4279. Min Act: 0.0000

Data Index: 1232595 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4516. Min Act: -0.0000

Data Index: 50228 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4263. Min Act: -0.0000

Data Index: 947514 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4199. Min Act: -0.0000

Data Index: 430301 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4085. Min Act: -0.0000

Data Index: 947930 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3784. Min Act: -0.0000

Data Index: 907014 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3931. Min Act: 0.0000

Data Index: 985184 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4013. Min Act: -0.0000

Data Index: 838138 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4179. Min Act: -0.0000

Data Index: 115308 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4001. Min Act: -0.0000

Data Index: 65143 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3954. Min Act: 0.0000

Data Index: 633666 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3820. Min Act: 0.0001

Data Index: 1113950 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1246980 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3398. Min Act: -0.0000

Data Index: 485895 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3864. Min Act: -0.0000

Data Index: 946796 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3484. Min Act: -0.0000

Data Index: 485033 (C4 (Web Text))

Max Activating Token Index: 279