Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.8030. Min Act: -0.0000

Data Index: 982845 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.6164. Min Act: -0.0000

Data Index: 920717 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.3678. Min Act: -0.0000

Data Index: 573904 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.4091. Min Act: -0.0000

Data Index: 1065490 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.3632. Min Act: -0.0000

Data Index: 971100 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.3906. Min Act: -0.0000

Data Index: 1005020 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.3380. Min Act: -0.0000

Data Index: 847941 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1332558 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.3522. Min Act: -0.0000

Data Index: 1314566 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.3862. Min Act: -0.0000

Data Index: 788168 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.1523. Min Act: -0.0000

Data Index: 220972 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.2462. Min Act: -0.0000

Data Index: 754774 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.2299. Min Act: -0.0000

Data Index: 112682 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.3257. Min Act: -0.0000

Data Index: 133550 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 2.8030. Min Range: -2.8030

Max Act: 2.0515. Min Act: -0.0000

Data Index: 15084 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.8030. Min Range: -2.8030

Max Act: 1.8074. Min Act: -0.0000

Data Index: 505140 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 2.8030. Min Range: -2.8030

Max Act: 1.9391. Min Act: -0.0000

Data Index: 601631 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 2.8030. Min Range: -2.8030

Max Act: 1.9259. Min Act: -0.0000

Data Index: 873150 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 2.8030. Min Range: -2.8030

Max Act: 1.9154. Min Act: -0.0000

Data Index: 680535 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 2.8030. Min Range: -2.8030

Max Act: 1.9749. Min Act: -0.0000

Data Index: 1021264 (C4 (Web Text))

Max Activating Token Index: 995