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

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

Neuron 69 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.8908. Min Act: -0.0001

Data Index: 375503 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.5217. Min Act: -0.0001

Data Index: 1084365 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.4575. Min Act: -0.0001

Data Index: 785656 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.4366. Min Act: -0.0001

Data Index: 648103 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.3969. Min Act: -0.0001

Data Index: 1304854 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.4217. Min Act: -0.0001

Data Index: 806101 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.2657. Min Act: -0.0001

Data Index: 916923 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.3673. Min Act: -0.0001

Data Index: 1339897 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.2017. Min Act: -0.0001

Data Index: 87678 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.2390. Min Act: -0.0001

Data Index: 1217352 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.0661. Min Act: -0.0001

Data Index: 913198 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.8908. Min Range: -1.8908

Max Act: 0.9221. Min Act: -0.0001

Data Index: 904457 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1355. Min Act: -0.0001

Data Index: 1168826 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.3678. Min Act: -0.0001

Data Index: 243144 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1214. Min Act: -0.0001

Data Index: 154535 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1550. Min Act: -0.0001

Data Index: 1012937 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.2257. Min Act: -0.0001

Data Index: 1053763 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.2882. Min Act: -0.0001

Data Index: 1331589 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1501. Min Act: -0.0001

Data Index: 1306149 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.8908. Min Range: -1.8908

Max Act: 1.1088. Min Act: -0.0001

Data Index: 1279992 (C4 (Web Text))

Max Activating Token Index: 342