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

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

Neuron 616 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: 3.9321. Min Range: -3.9321

Max Act: 3.9321. Min Act: -0.0002

Data Index: 755593 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.8510. Min Act: -0.0002

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7828. Min Act: -0.0002

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.7331. Min Act: -0.0002

Data Index: 813797 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.6379. Min Act: -0.0002

Data Index: 606429 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5929. Min Act: -0.0002

Data Index: 643374 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5477. Min Act: -0.0002

Data Index: 768935 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4646. Min Act: -0.0002

Data Index: 651890 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5666. Min Act: -0.0002

Data Index: 507576 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.5082. Min Act: -0.0002

Data Index: 232834 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4803. Min Act: -0.0002

Data Index: 285195 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4855. Min Act: -0.0002

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4362. Min Act: -0.0002

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.3805. Min Act: -0.0002

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4755. Min Act: -0.0002

Data Index: 123292 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.4243. Min Act: -0.0002

Data Index: 766490 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.3246. Min Act: -0.0002

Data Index: 360735 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.2909. Min Act: -0.0002

Data Index: 475029 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.2686. Min Act: -0.0002

Data Index: 347195 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 3.9321. Min Range: -3.9321

Max Act: 3.3448. Min Act: -0.0002

Data Index: 74019 (C4 (Web Text))

Max Activating Token Index: 141