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

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

Neuron 2966 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: 1.7663. Min Range: -1.7663

Max Act: 1.7663. Min Act: -0.0002

Data Index: 133259 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4876. Min Act: -0.0002

Data Index: 1305215 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4747. Min Act: -0.0002

Data Index: 567915 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4299. Min Act: -0.0002

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4401. Min Act: -0.0002

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4232. Min Act: -0.0002

Data Index: 421268 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4113. Min Act: -0.0002

Data Index: 131038 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4037. Min Act: -0.0002

Data Index: 354491 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4162. Min Act: -0.0002

Data Index: 792719 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3696. Min Act: -0.0002

Data Index: 503449 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3860. Min Act: -0.0002

Data Index: 634226 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3581. Min Act: -0.0002

Data Index: 1049082 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3419. Min Act: -0.0002

Data Index: 671008 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3490. Min Act: -0.0002

Data Index: 1055614 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3198. Min Act: -0.0002

Data Index: 1633390 (Python Code)

Max Activating Token Index: 325

Text #15

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3407. Min Act: -0.0002

Data Index: 114614 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3668. Min Act: -0.0002

Data Index: 742794 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3593. Min Act: -0.0002

Data Index: 440209 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3224. Min Act: -0.0002

Data Index: 382034 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3138. Min Act: -0.0002

Data Index: 663139 (C4 (Web Text))

Max Activating Token Index: 748