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

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

Neuron 4226 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.6143. Min Act: -0.0002

Data Index: 1145899 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.5787. Min Act: -0.0002

Data Index: 946117 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.5627. Min Act: -0.0002

Data Index: 290548 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.5705. Min Act: -0.0002

Data Index: 447920 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.5844. Min Act: -0.0002

Data Index: 823721 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.5084. Min Act: -0.0002

Data Index: 588176 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.5325. Min Act: -0.0002

Data Index: 627130 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.5126. Min Act: -0.0002

Data Index: 200786 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.4831. Min Act: -0.0002

Data Index: 969407 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.4511. Min Act: -0.0002

Data Index: 769376 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.4400. Min Act: -0.0002

Data Index: 632215 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.4082. Min Act: -0.0002

Data Index: 1353486 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.4187. Min Act: -0.0003

Data Index: 1134322 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.3627. Min Act: -0.0002

Data Index: 398097 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.3930. Min Act: -0.0002

Data Index: 961276 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.3850. Min Act: -0.0002

Data Index: 1253153 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.3606. Min Act: -0.0002

Data Index: 1195022 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.3819. Min Act: -0.0002

Data Index: 505072 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.3523. Min Act: -0.0002

Data Index: 141782 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.6143. Min Range: -1.6143

Max Act: 1.3384. Min Act: -0.0002

Data Index: 49183 (C4 (Web Text))

Max Activating Token Index: 286