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

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

Neuron 3199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.4640. Min Act: -0.0001

Data Index: 380129 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.5259. Min Act: -0.0001

Data Index: 835818 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.9439. Min Act: -0.0001

Data Index: 1200953 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.8848. Min Act: -0.0001

Data Index: 768474 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.8500. Min Act: -0.0001

Data Index: 863816 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.8706. Min Act: -0.0001

Data Index: 309181 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.9275. Min Act: -0.0001

Data Index: 1036853 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.8784. Min Act: -0.0001

Data Index: 1097857 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.8364. Min Act: -0.0001

Data Index: 114196 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.8895. Min Act: -0.0001

Data Index: 441677 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.7501. Min Act: -0.0001

Data Index: 188429 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.7647. Min Act: -0.0001

Data Index: 109658 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.7464. Min Act: -0.0001

Data Index: 1143696 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.7138. Min Act: -0.0001

Data Index: 1060278 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.7579. Min Act: -0.0001

Data Index: 917178 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.7634. Min Act: -0.0001

Data Index: 586149 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.7204. Min Act: -0.0001

Data Index: 277205 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.6866. Min Act: -0.0001

Data Index: 1261376 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.6960. Min Act: -0.0001

Data Index: 443205 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.6968. Min Act: -0.0001

Data Index: 278589 (C4 (Web Text))

Max Activating Token Index: 82