Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 883 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4643. Min Act: -0.0003

Data Index: 551624 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4555. Min Act: -0.0003

Data Index: 103094 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4695. Min Act: -0.0003

Data Index: 240779 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4516. Min Act: -0.0003

Data Index: 1305809 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4500. Min Act: -0.0003

Data Index: 1145321 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4540. Min Act: -0.0003

Data Index: 107635 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4537. Min Act: -0.0003

Data Index: 756897 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4391. Min Act: -0.0003

Data Index: 803638 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4139. Min Act: -0.0003

Data Index: 851997 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4249. Min Act: -0.0003

Data Index: 556518 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4532. Min Act: -0.0003

Data Index: 1032933 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4370. Min Act: -0.0003

Data Index: 141561 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4199. Min Act: -0.0003

Data Index: 790814 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4253. Min Act: -0.0003

Data Index: 344940 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4260. Min Act: -0.0003

Data Index: 207041 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4390. Min Act: -0.0003

Data Index: 1096660 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3969. Min Act: -0.0003

Data Index: 1244724 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4131. Min Act: -0.0003

Data Index: 1255753 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3974. Min Act: -0.0003

Data Index: 622246 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4132. Min Act: -0.0003

Data Index: 700410 (C4 (Web Text))

Max Activating Token Index: 317