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

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

Neuron 919 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1107. Min Range: -2.1107

Max Act: 2.1107. Min Act: -0.0000

Data Index: 101893 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1155650 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1345665 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.3004. Min Act: -0.0000

Data Index: 433020 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.2653. Min Act: -0.0000

Data Index: 320109 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.2974. Min Act: -0.0000

Data Index: 366324 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.2865. Min Act: -0.0000

Data Index: 426194 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.1344. Min Act: -0.0000

Data Index: 676413 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1257962 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.2345. Min Act: -0.0000

Data Index: 457492 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.0717. Min Act: -0.0000

Data Index: 769064 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 2.1107. Min Range: -2.1107

Max Act: 0.9923. Min Act: -0.0000

Data Index: 666922 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.1167. Min Act: -0.0000

Data Index: 836985 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1214199 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 2.1107. Min Range: -2.1107

Max Act: 0.9962. Min Act: -0.0000

Data Index: 223263 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 2.1107. Min Range: -2.1107

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1110687 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.0546. Min Act: -0.0000

Data Index: 136703 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.0932. Min Act: -0.0000

Data Index: 643988 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1121891 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 2.1107. Min Range: -2.1107

Max Act: 1.0372. Min Act: -0.0000

Data Index: 434066 (C4 (Web Text))

Max Activating Token Index: 98