Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2205 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6840. Min Act: -0.0001

Data Index: 855105 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4671. Min Act: -0.0001

Data Index: 1155797 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5904. Min Act: -0.0001

Data Index: 31014 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3448. Min Act: -0.0001

Data Index: 571654 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5351. Min Act: -0.0001

Data Index: 248101 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4295. Min Act: -0.0001

Data Index: 127152 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3404. Min Act: -0.0001

Data Index: 988827 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3419. Min Act: -0.0001

Data Index: 372861 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2843. Min Act: -0.0001

Data Index: 1227219 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3188. Min Act: -0.0001

Data Index: 108273 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2628. Min Act: -0.0001

Data Index: 771922 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2444. Min Act: -0.0001

Data Index: 759509 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3234. Min Act: -0.0001

Data Index: 223557 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1355776 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3045. Min Act: -0.0001

Data Index: 1027734 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.1752. Min Act: -0.0001

Data Index: 388945 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2785. Min Act: -0.0001

Data Index: 696106 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2741. Min Act: -0.0001

Data Index: 517107 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2049. Min Act: -0.0001

Data Index: 272785 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2351. Min Act: -0.0001

Data Index: 328913 (C4 (Web Text))

Max Activating Token Index: 297