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

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

Neuron 3118 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: 1.8272. Min Range: -1.8272

Max Act: 1.8272. Min Act: -0.0001

Data Index: 542328 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5522. Min Act: -0.0001

Data Index: 570873 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5383. Min Act: -0.0001

Data Index: 265242 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4728. Min Act: -0.0001

Data Index: 919751 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4580. Min Act: -0.0001

Data Index: 191902 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4834. Min Act: -0.0001

Data Index: 207152 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4635. Min Act: -0.0001

Data Index: 723929 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3580. Min Act: -0.0001

Data Index: 873961 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3726. Min Act: -0.0001

Data Index: 16788 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3695. Min Act: -0.0001

Data Index: 190305 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4551. Min Act: -0.0001

Data Index: 447853 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4133. Min Act: -0.0001

Data Index: 476480 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4089. Min Act: -0.0001

Data Index: 1023277 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4295. Min Act: -0.0001

Data Index: 26843 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3913. Min Act: -0.0001

Data Index: 585902 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4233. Min Act: -0.0001

Data Index: 1108137 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3691. Min Act: -0.0001

Data Index: 1243122 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3599. Min Act: -0.0001

Data Index: 116490 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3021. Min Act: -0.0001

Data Index: 1247963 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3488. Min Act: -0.0001

Data Index: 1023675 (C4 (Web Text))

Max Activating Token Index: 32