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

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

Neuron 4204 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.5106. Min Act: -0.0000

Data Index: 685088 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4009. Min Act: -0.0000

Data Index: 708684 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1252179 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1139620 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3530. Min Act: -0.0000

Data Index: 793621 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1308352 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1099943 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3203. Min Act: -0.0000

Data Index: 782624 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3680. Min Act: -0.0000

Data Index: 382962 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3425. Min Act: -0.0000

Data Index: 301330 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3353. Min Act: -0.0000

Data Index: 861232 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1236881 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1006163 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3144. Min Act: -0.0000

Data Index: 599013 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.2914. Min Act: -0.0000

Data Index: 105449 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.2941. Min Act: -0.0000

Data Index: 293126 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3086. Min Act: -0.0000

Data Index: 493742 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3046. Min Act: -0.0000

Data Index: 740987 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.2869. Min Act: -0.0000

Data Index: 219354 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.2604. Min Act: -0.0000

Data Index: 491364 (C4 (Web Text))

Max Activating Token Index: 933