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

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

Neuron 1040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5838. Min Act: -0.0001

Data Index: 622768 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5882. Min Act: -0.0001

Data Index: 170223 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5511. Min Act: -0.0001

Data Index: 1656486 (Python Code)

Max Activating Token Index: 483

Text #3

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5398. Min Act: -0.0001

Data Index: 259161 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5338. Min Act: -0.0001

Data Index: 148176 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5321. Min Act: -0.0001

Data Index: 1580223 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5278. Min Act: -0.0001

Data Index: 1527270 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1524695 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5127. Min Act: -0.0001

Data Index: 1474841 (Python Code)

Max Activating Token Index: 769

Text #9

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5220. Min Act: -0.0001

Data Index: 788131 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5191. Min Act: -0.0001

Data Index: 1533502 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4672. Min Act: -0.0001

Data Index: 1474122 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5184. Min Act: -0.0001

Data Index: 1471717 (Python Code)

Max Activating Token Index: 231

Text #13

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5377. Min Act: -0.0001

Data Index: 1395758 (Python Code)

Max Activating Token Index: 601

Text #14

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5320. Min Act: -0.0001

Data Index: 1641361 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1409175 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5047. Min Act: -0.0001

Data Index: 303291 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4981. Min Act: -0.0001

Data Index: 1555529 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4957. Min Act: -0.0001

Data Index: 1460828 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4968. Min Act: -0.0001

Data Index: 1445811 (Python Code)

Max Activating Token Index: 115