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

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

Neuron 6088 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.9181. Min Act: -0.0000

Data Index: 471228 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.4606. Min Act: -0.0000

Data Index: 1200469 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.3304. Min Act: -0.0000

Data Index: 64975 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.1927. Min Act: -0.0000

Data Index: 470413 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.0661. Min Act: -0.0000

Data Index: 825778 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.9250. Min Act: -0.0000

Data Index: 395591 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.8922. Min Act: -0.0000

Data Index: 1310580 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.7588. Min Act: -0.0000

Data Index: 427217 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.8096. Min Act: -0.0000

Data Index: 460269 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.7572. Min Act: -0.0000

Data Index: 1246088 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.7483. Min Act: -0.0000

Data Index: 187848 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.6689. Min Act: -0.0000

Data Index: 1043027 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.5472. Min Act: -0.0000

Data Index: 977873 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.5348. Min Act: -0.0000

Data Index: 727271 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.6206. Min Act: -0.0000

Data Index: 761848 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1171680 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.5535. Min Act: -0.0000

Data Index: 868725 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.4074. Min Act: -0.0000

Data Index: 950818 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1296937 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.3889. Min Act: -0.0000

Data Index: 669088 (C4 (Web Text))

Max Activating Token Index: 327