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

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

Neuron 4691 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.7431. Min Act: -0.0000

Data Index: 441139 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.8131. Min Act: -0.0000

Data Index: 985974 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.8020. Min Act: -0.0000

Data Index: 743340 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.6736. Min Act: -0.0000

Data Index: 278153 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.7515. Min Act: -0.0000

Data Index: 1276397 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.6026. Min Act: -0.0000

Data Index: 862635 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.6773. Min Act: -0.0000

Data Index: 454075 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.6393. Min Act: -0.0000

Data Index: 995859 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.6276. Min Act: -0.0000

Data Index: 455494 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.5790. Min Act: -0.0000

Data Index: 236984 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.5589. Min Act: -0.0000

Data Index: 322268 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.5435. Min Act: -0.0000

Data Index: 118389 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.5578. Min Act: -0.0000

Data Index: 202683 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.4464. Min Act: -0.0000

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.4470. Min Act: -0.0000

Data Index: 294733 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.6125. Min Act: -0.0000

Data Index: 75078 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.6038. Min Act: -0.0000

Data Index: 155652 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.5115. Min Act: -0.0000

Data Index: 32195 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1148738 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.8131. Min Range: -1.8131

Max Act: 1.4885. Min Act: -0.0000

Data Index: 13836 (C4 (Web Text))

Max Activating Token Index: 598