Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3955 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1094006 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.6658. Min Act: -0.0000

Data Index: 599342 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1229880 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.6868. Min Act: -0.0000

Data Index: 1108899 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5607. Min Act: -0.0000

Data Index: 449373 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5297. Min Act: -0.0001

Data Index: 714385 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5525. Min Act: -0.0001

Data Index: 23850 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5287. Min Act: -0.0000

Data Index: 715811 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.5663. Min Act: -0.0001

Data Index: 460582 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4248. Min Act: -0.0001

Data Index: 712547 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3760. Min Act: -0.0001

Data Index: 267311 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3542. Min Act: -0.0000

Data Index: 395833 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3525. Min Act: -0.0000

Data Index: 23392 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3519. Min Act: -0.0001

Data Index: 526840 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3171. Min Act: -0.0000

Data Index: 696027 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.4165. Min Act: -0.0001

Data Index: 862559 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1211825 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3997. Min Act: -0.0001

Data Index: 1107306 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.2945. Min Act: -0.0001

Data Index: 965844 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.7895. Min Range: -1.7895

Max Act: 1.3354. Min Act: -0.0001

Data Index: 192653 (C4 (Web Text))

Max Activating Token Index: 140