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

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

Neuron 948 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.5055. Min Act: -0.0002

Data Index: 1409829 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4643. Min Act: -0.0002

Data Index: 186814 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4399. Min Act: -0.0002

Data Index: 170764 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4251. Min Act: -0.0002

Data Index: 599759 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4350. Min Act: -0.0002

Data Index: 300457 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4307. Min Act: -0.0002

Data Index: 477748 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4270. Min Act: -0.0002

Data Index: 238690 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4210. Min Act: -0.0002

Data Index: 590353 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4216. Min Act: -0.0002

Data Index: 435649 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4305. Min Act: -0.0003

Data Index: 1331300 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4305. Min Act: -0.0002

Data Index: 943269 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4169. Min Act: -0.0002

Data Index: 1564602 (Python Code)

Max Activating Token Index: 506

Text #12

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4124. Min Act: -0.0002

Data Index: 892468 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4210. Min Act: -0.0002

Data Index: 1649273 (Python Code)

Max Activating Token Index: 999

Text #14

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4147. Min Act: -0.0002

Data Index: 967472 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4164. Min Act: -0.0002

Data Index: 1143611 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4103. Min Act: -0.0002

Data Index: 1125010 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4121. Min Act: -0.0002

Data Index: 1219118 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4033. Min Act: -0.0002

Data Index: 101231 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4019. Min Act: -0.0002

Data Index: 187261 (C4 (Web Text))

Max Activating Token Index: 688