Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 104 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0764. Min Range: -1.0764

Max Act: 1.0737. Min Act: -0.0001

Data Index: 897931 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.0764. Min Range: -1.0764

Max Act: 1.0764. Min Act: -0.0001

Data Index: 38293 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.0764. Min Range: -1.0764

Max Act: 1.0279. Min Act: -0.0001

Data Index: 109211 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9729. Min Act: -0.0001

Data Index: 715076 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9302. Min Act: -0.0001

Data Index: 1288458 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9419. Min Act: -0.0001

Data Index: 199730 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9299. Min Act: -0.0001

Data Index: 1211089 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9137. Min Act: -0.0001

Data Index: 166269 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8785. Min Act: -0.0001

Data Index: 356763 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8665. Min Act: -0.0001

Data Index: 891681 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8842. Min Act: -0.0001

Data Index: 294620 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9012. Min Act: -0.0001

Data Index: 720417 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8989. Min Act: -0.0001

Data Index: 815096 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8707. Min Act: -0.0001

Data Index: 189322 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8791. Min Act: -0.0001

Data Index: 173560 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8287. Min Act: -0.0001

Data Index: 536602 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8519. Min Act: -0.0001

Data Index: 312865 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8200. Min Act: -0.0001

Data Index: 1108241 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8183. Min Act: -0.0001

Data Index: 1304334 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8387. Min Act: -0.0001

Data Index: 1274120 (C4 (Web Text))

Max Activating Token Index: 441