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

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

Neuron 3097 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: 0.6892. Min Range: -0.6892

Max Act: 0.6892. Min Act: -0.0002

Data Index: 844934 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6293. Min Act: -0.0003

Data Index: 668573 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6193. Min Act: -0.0003

Data Index: 109974 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6036. Min Act: -0.0002

Data Index: 319267 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6056. Min Act: -0.0002

Data Index: 1094266 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5775. Min Act: -0.0002

Data Index: 267226 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5864. Min Act: -0.0003

Data Index: 1177948 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5758. Min Act: -0.0002

Data Index: 1280990 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5862. Min Act: -0.0002

Data Index: 313264 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5726. Min Act: -0.0003

Data Index: 415351 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5683. Min Act: -0.0002

Data Index: 119755 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5658. Min Act: -0.0002

Data Index: 1209607 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5747. Min Act: -0.0002

Data Index: 671384 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5828. Min Act: -0.0002

Data Index: 427340 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5705. Min Act: -0.0002

Data Index: 677009 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5630. Min Act: -0.0002

Data Index: 1301338 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5703. Min Act: -0.0002

Data Index: 967062 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5615. Min Act: -0.0002

Data Index: 166512 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5649. Min Act: -0.0003

Data Index: 279083 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5663. Min Act: -0.0003

Data Index: 366376 (C4 (Web Text))

Max Activating Token Index: 259