Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 473 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1055085 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.1011. Min Act: -0.0001

Data Index: 913860 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.1016. Min Act: -0.0001

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0939. Min Act: -0.0001

Data Index: 427113 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0949. Min Act: -0.0001

Data Index: 298343 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0911. Min Act: -0.0001

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0888. Min Act: -0.0001

Data Index: 268120 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0886. Min Act: -0.0001

Data Index: 906362 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0964. Min Act: -0.0001

Data Index: 35714 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0805. Min Act: -0.0001

Data Index: 253611 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0849. Min Act: -0.0001

Data Index: 29731 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0787. Min Act: -0.0001

Data Index: 990442 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1087139 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0810. Min Act: -0.0001

Data Index: 464216 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1325167 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0765. Min Act: -0.0001

Data Index: 844081 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0761. Min Act: -0.0001

Data Index: 229359 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1248427 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0797. Min Act: -0.0001

Data Index: 641577 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0782. Min Act: -0.0001

Data Index: 257972 (C4 (Web Text))

Max Activating Token Index: 99