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

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

Neuron 911 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.8665. Min Act: -0.0000

Data Index: 1166967 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.8339. Min Act: -0.0000

Data Index: 1357029 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.5094. Min Act: -0.0000

Data Index: 1183527 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.7423. Min Act: -0.0000

Data Index: 107465 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.4466. Min Act: -0.0000

Data Index: 1539242 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.4348. Min Act: -0.0000

Data Index: 252329 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.6493. Min Act: -0.0000

Data Index: 1044397 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.4877. Min Act: -0.0000

Data Index: 46308 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.4897. Min Act: -0.0000

Data Index: 668414 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.2100. Min Act: -0.0000

Data Index: 25331 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.2370. Min Act: -0.0000

Data Index: 713297 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.1197. Min Act: -0.0000

Data Index: 1252218 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 2.8665. Min Range: -2.8665

Max Act: 1.9744. Min Act: -0.0000

Data Index: 454306 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 2.8665. Min Range: -2.8665

Max Act: 2.2141. Min Act: -0.0000

Data Index: 1035891 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 2.8665. Min Range: -2.8665

Max Act: 1.7853. Min Act: -0.0000

Data Index: 13812 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 2.8665. Min Range: -2.8665

Max Act: 1.7241. Min Act: -0.0000

Data Index: 1162738 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 2.8665. Min Range: -2.8665

Max Act: 1.7844. Min Act: -0.0000

Data Index: 939852 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 2.8665. Min Range: -2.8665

Max Act: 1.7278. Min Act: -0.0000

Data Index: 47293 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 2.8665. Min Range: -2.8665

Max Act: 1.8853. Min Act: -0.0000

Data Index: 1175351 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 2.8665. Min Range: -2.8665

Max Act: 1.6105. Min Act: -0.0000

Data Index: 29334 (C4 (Web Text))

Max Activating Token Index: 294