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

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

Neuron 2375 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1420. Min Range: -2.1420

Max Act: 2.1420. Min Act: -0.0000

Data Index: 1157565 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.9396. Min Act: -0.0000

Data Index: 1248274 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 2.1420. Min Range: -2.1420

Max Act: 2.1054. Min Act: -0.0000

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.9364. Min Act: -0.0000

Data Index: 689108 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.6424. Min Act: -0.0000

Data Index: 1145939 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.7159. Min Act: -0.0000

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.5228. Min Act: -0.0000

Data Index: 408675 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.5708. Min Act: -0.0000

Data Index: 736016 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.4538. Min Act: -0.0000

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.3691. Min Act: -0.0000

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.4680. Min Act: -0.0000

Data Index: 971897 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.3705. Min Act: -0.0000

Data Index: 354447 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.5145. Min Act: -0.0000

Data Index: 367081 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.3570. Min Act: -0.0000

Data Index: 79217 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.4163. Min Act: -0.0000

Data Index: 292790 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.4161. Min Act: -0.0000

Data Index: 335764 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.4035. Min Act: -0.0000

Data Index: 488195 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.3080. Min Act: -0.0000

Data Index: 964184 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 2.1420. Min Range: -2.1420

Max Act: 1.4099. Min Act: -0.0000

Data Index: 165459 (C4 (Web Text))

Max Activating Token Index: 204