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

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

Neuron 2285 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.9925. Min Act: -0.0000

Data Index: 278415 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.8335. Min Act: -0.0000

Data Index: 128006 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.8258. Min Act: -0.0000

Data Index: 637436 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.6707. Min Act: -0.0000

Data Index: 21289 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.9660. Min Act: -0.0000

Data Index: 25170 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.6819. Min Act: -0.0000

Data Index: 182192 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.6280. Min Act: -0.0000

Data Index: 808893 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.7575. Min Act: -0.0000

Data Index: 496319 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.7481. Min Act: -0.0000

Data Index: 1095191 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.7078. Min Act: -0.0000

Data Index: 397066 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.7369. Min Act: -0.0000

Data Index: 267858 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.6710. Min Act: -0.0000

Data Index: 832633 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.6500. Min Act: -0.0000

Data Index: 500428 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.4981. Min Act: -0.0000

Data Index: 1048637 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.6412. Min Act: -0.0000

Data Index: 993627 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.5979. Min Act: -0.0000

Data Index: 509433 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.5991. Min Act: -0.0000

Data Index: 593598 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.5891. Min Act: -0.0000

Data Index: 268032 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.4705. Min Act: -0.0000

Data Index: 1092390 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 2.9925. Min Range: -2.9925

Max Act: 2.5242. Min Act: -0.0000

Data Index: 1198619 (C4 (Web Text))

Max Activating Token Index: 167