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

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

Neuron 3804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.5924. Min Act: -0.0000

Data Index: 438254 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.9106. Min Act: -0.0000

Data Index: 249289 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.8256. Min Act: -0.0000

Data Index: 1591535 (Python Code)

Max Activating Token Index: 992

Text #3

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.4806. Min Act: -0.0000

Data Index: 1234609 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.6109. Min Act: -0.0000

Data Index: 1357624 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.3970. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.3592. Min Act: -0.0000

Data Index: 1999 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.2971. Min Act: -0.0000

Data Index: 495480 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.4259. Min Act: -0.0000

Data Index: 171682 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.2677. Min Act: -0.0000

Data Index: 1262020 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.2755. Min Act: -0.0000

Data Index: 9296 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.4337. Min Act: -0.0000

Data Index: 1631170 (Python Code)

Max Activating Token Index: 861

Text #12

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.3042. Min Act: -0.0000

Data Index: 654760 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.5335. Min Act: -0.0000

Data Index: 1238382 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.2259. Min Act: -0.0000

Data Index: 805169 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.3133. Min Act: -0.0000

Data Index: 550189 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.2804. Min Act: -0.0000

Data Index: 1144366 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.4630. Min Act: -0.0000

Data Index: 593380 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.1309. Min Act: -0.0000

Data Index: 795100 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 3.9106. Min Range: -3.9106

Max Act: 3.1964. Min Act: -0.0000

Data Index: 955916 (C4 (Web Text))

Max Activating Token Index: 630