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

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

Neuron 3231 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: 0.4870. Min Range: -0.4870

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1199124 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4665. Min Act: -0.0000

Data Index: 88331 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4361. Min Act: -0.0000

Data Index: 342881 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4646. Min Act: -0.0000

Data Index: 653077 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4623. Min Act: -0.0000

Data Index: 436808 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4544. Min Act: -0.0000

Data Index: 802606 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1165642 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4684. Min Act: -0.0000

Data Index: 631704 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4335. Min Act: -0.0000

Data Index: 916457 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1108469 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1170937 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4224. Min Act: -0.0000

Data Index: 577217 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4304. Min Act: -0.0000

Data Index: 195151 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1208888 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4088. Min Act: -0.0000

Data Index: 40846 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1290796 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3918. Min Act: -0.0000

Data Index: 385869 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3882. Min Act: -0.0000

Data Index: 431442 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3905. Min Act: -0.0000

Data Index: 319603 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4110. Min Act: -0.0000

Data Index: 822419 (C4 (Web Text))

Max Activating Token Index: 907