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

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

Neuron 768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6941. Min Act: -0.0000

Data Index: 859243 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7207. Min Act: -0.0000

Data Index: 40767 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6431. Min Act: -0.0000

Data Index: 881781 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.5739. Min Act: -0.0000

Data Index: 5036 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6749. Min Act: -0.0000

Data Index: 910989 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6749. Min Act: -0.0000

Data Index: 567355 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6703. Min Act: -0.0000

Data Index: 183138 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6738. Min Act: -0.0000

Data Index: 784102 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7310. Min Act: -0.0000

Data Index: 767954 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6194. Min Act: -0.0000

Data Index: 68229 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6726. Min Act: -0.0000

Data Index: 948127 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7206. Min Act: -0.0000

Data Index: 849812 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7065. Min Act: -0.0000

Data Index: 1256442 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6789. Min Act: -0.0000

Data Index: 366583 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7086. Min Act: -0.0000

Data Index: 1041839 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7127. Min Act: -0.0000

Data Index: 670673 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6543. Min Act: -0.0000

Data Index: 468001 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6047. Min Act: -0.0000

Data Index: 1063179 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.5909. Min Act: -0.0000

Data Index: 635899 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6031. Min Act: -0.0000

Data Index: 750633 (C4 (Web Text))

Max Activating Token Index: 283