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

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

Neuron 1086 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: 2.4439. Min Range: -2.4439

Max Act: 2.4439. Min Act: -0.0002

Data Index: 965792 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 2.4439. Min Range: -2.4439

Max Act: 2.1341. Min Act: -0.0002

Data Index: 1038267 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 2.4439. Min Range: -2.4439

Max Act: 2.0228. Min Act: -0.0002

Data Index: 750209 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 2.4439. Min Range: -2.4439

Max Act: 2.0834. Min Act: -0.0002

Data Index: 829541 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 2.4439. Min Range: -2.4439

Max Act: 2.0285. Min Act: -0.0002

Data Index: 635627 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.9579. Min Act: -0.0002

Data Index: 130800 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8810. Min Act: -0.0002

Data Index: 722400 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.9259. Min Act: -0.0002

Data Index: 44425 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.9106. Min Act: -0.0002

Data Index: 146635 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.9178. Min Act: -0.0002

Data Index: 348277 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8760. Min Act: -0.0002

Data Index: 1240096 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8818. Min Act: -0.0002

Data Index: 1256935 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8299. Min Act: -0.0002

Data Index: 354017 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8409. Min Act: -0.0002

Data Index: 1133570 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8053. Min Act: -0.0002

Data Index: 835352 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8633. Min Act: -0.0002

Data Index: 56803 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8009. Min Act: -0.0002

Data Index: 252380 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8152. Min Act: -0.0003

Data Index: 339759 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8305. Min Act: -0.0002

Data Index: 1300460 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 2.4439. Min Range: -2.4439

Max Act: 1.8176. Min Act: -0.0002

Data Index: 910027 (C4 (Web Text))

Max Activating Token Index: 253