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

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

Neuron 2527 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: 1.8405. Min Range: -1.8405

Max Act: 1.6577. Min Act: -0.0001

Data Index: 261620 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.8405. Min Act: -0.0001

Data Index: 473566 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6173. Min Act: -0.0001

Data Index: 1247181 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.3029. Min Act: -0.0001

Data Index: 1145324 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6913. Min Act: -0.0001

Data Index: 636068 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.3844. Min Act: -0.0001

Data Index: 832091 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.2105. Min Act: -0.0001

Data Index: 1076201 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.5052. Min Act: -0.0001

Data Index: 350244 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.3421. Min Act: -0.0001

Data Index: 189611 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.5587. Min Act: -0.0001

Data Index: 1303113 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4131. Min Act: -0.0001

Data Index: 688856 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.5328. Min Act: -0.0001

Data Index: 438954 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6198. Min Act: -0.0001

Data Index: 1278620 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4122. Min Act: -0.0001

Data Index: 762240 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.3984. Min Act: -0.0001

Data Index: 1299118 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.2237. Min Act: -0.0001

Data Index: 840651 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4292. Min Act: -0.0001

Data Index: 17061 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4704. Min Act: -0.0001

Data Index: 560548 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4827. Min Act: -0.0001

Data Index: 120743 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4296. Min Act: -0.0001

Data Index: 859749 (C4 (Web Text))

Max Activating Token Index: 893