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

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

Neuron 3593 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: 2.0462. Min Range: -2.0462

Max Act: 1.8697. Min Act: -0.0000

Data Index: 233127 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 2.0462. Min Range: -2.0462

Max Act: 2.0462. Min Act: -0.0000

Data Index: 465765 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.8244. Min Act: -0.0000

Data Index: 508251 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 2.0462. Min Range: -2.0462

Max Act: 2.0135. Min Act: -0.0000

Data Index: 273389 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1039089 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7630. Min Act: -0.0000

Data Index: 280051 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7721. Min Act: -0.0000

Data Index: 149649 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7053. Min Act: -0.0000

Data Index: 804863 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7114. Min Act: -0.0000

Data Index: 906614 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.6394. Min Act: -0.0000

Data Index: 398767 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.8026. Min Act: -0.0000

Data Index: 955515 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7096. Min Act: -0.0000

Data Index: 1176440 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7058. Min Act: -0.0000

Data Index: 699313 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.6473. Min Act: -0.0000

Data Index: 1179835 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1197230 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7758. Min Act: -0.0000

Data Index: 939502 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7270. Min Act: -0.0000

Data Index: 808493 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.7217. Min Act: -0.0000

Data Index: 62369 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.6343. Min Act: -0.0000

Data Index: 121419 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 2.0462. Min Range: -2.0462

Max Act: 1.6122. Min Act: -0.0000

Data Index: 780553 (C4 (Web Text))

Max Activating Token Index: 325