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

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

Neuron 2274 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: 1.0431. Min Range: -1.0431

Max Act: 0.9609. Min Act: -0.0001

Data Index: 198686 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.0431. Min Range: -1.0431

Max Act: 1.0431. Min Act: -0.0001

Data Index: 961265 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8903. Min Act: -0.0001

Data Index: 1171411 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8713. Min Act: -0.0001

Data Index: 372984 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8620. Min Act: -0.0001

Data Index: 558866 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8524. Min Act: -0.0001

Data Index: 490866 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8513. Min Act: -0.0001

Data Index: 823178 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8133. Min Act: -0.0001

Data Index: 1175119 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7897. Min Act: -0.0001

Data Index: 1317355 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8174. Min Act: -0.0001

Data Index: 193062 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8140. Min Act: -0.0001

Data Index: 118999 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7647. Min Act: -0.0001

Data Index: 877964 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7766. Min Act: -0.0001

Data Index: 620688 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7843. Min Act: -0.0001

Data Index: 61793 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8045. Min Act: -0.0001

Data Index: 255109 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7787. Min Act: -0.0001

Data Index: 341733 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.8198. Min Act: -0.0001

Data Index: 7551 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7869. Min Act: -0.0001

Data Index: 506528 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7932. Min Act: -0.0001

Data Index: 864237 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.0431. Min Range: -1.0431

Max Act: 0.7886. Min Act: -0.0001

Data Index: 8546 (C4 (Web Text))

Max Activating Token Index: 915