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

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

Neuron 1187 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0001

Data Index: 526123 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1052345 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0366. Min Act: -0.0001

Data Index: 844033 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0333. Min Act: -0.0001

Data Index: 857246 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1029715 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0305. Min Act: -0.0001

Data Index: 320722 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0301. Min Act: -0.0001

Data Index: 30273 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0290. Min Act: -0.0001

Data Index: 391813 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0286. Min Act: -0.0001

Data Index: 215222 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1041314 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0297. Min Act: -0.0001

Data Index: 645146 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0298. Min Act: -0.0001

Data Index: 844896 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0270. Min Act: -0.0001

Data Index: 380642 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0305. Min Act: -0.0001

Data Index: 301245 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0314. Min Act: -0.0001

Data Index: 411120 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1009258 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0269. Min Act: -0.0001

Data Index: 364216 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0286. Min Act: -0.0001

Data Index: 648438 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1149024 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0290. Min Act: -0.0001

Data Index: 739104 (C4 (Web Text))

Max Activating Token Index: 34