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

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

Neuron 1332 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.9814. Min Act: -0.0000

Data Index: 757206 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7411. Min Act: -0.0001

Data Index: 777047 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1297895 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7496. Min Act: -0.0000

Data Index: 428248 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7139. Min Act: -0.0001

Data Index: 501036 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6681. Min Act: -0.0000

Data Index: 938601 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6779. Min Act: -0.0000

Data Index: 214803 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1036731 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6894. Min Act: -0.0000

Data Index: 691879 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1132979 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1298479 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1292070 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6293. Min Act: -0.0000

Data Index: 35949 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1186882 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1338424 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6076. Min Act: -0.0001

Data Index: 183731 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6440. Min Act: -0.0000

Data Index: 307524 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6374. Min Act: -0.0000

Data Index: 90815 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5958. Min Act: -0.0000

Data Index: 146508 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5963. Min Act: -0.0000

Data Index: 107602 (C4 (Web Text))

Max Activating Token Index: 179