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

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

Neuron 3603 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.7884. Min Act: -0.0000

Data Index: 728023 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.5909. Min Act: -0.0000

Data Index: 793379 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1164243 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4330. Min Act: -0.0000

Data Index: 1014745 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1029401 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1302967 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.1910. Min Act: -0.0000

Data Index: 384985 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1357523 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.0959. Min Act: -0.0000

Data Index: 201536 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.0555. Min Act: -0.0000

Data Index: 224451 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.0291. Min Act: -0.0000

Data Index: 829945 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.7884. Min Range: -1.7884

Max Act: 0.9382. Min Act: -0.0000

Data Index: 431035 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.1445. Min Act: -0.0000

Data Index: 800859 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.7884. Min Range: -1.7884

Max Act: 0.8860. Min Act: -0.0000

Data Index: 19183 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 1.7884. Min Range: -1.7884

Max Act: 0.9780. Min Act: -0.0000

Data Index: 903982 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.7884. Min Range: -1.7884

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1073383 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.0170. Min Act: -0.0000

Data Index: 740245 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.7884. Min Range: -1.7884

Max Act: 0.8874. Min Act: -0.0000

Data Index: 514831 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.7884. Min Range: -1.7884

Max Act: 0.9507. Min Act: -0.0000

Data Index: 761747 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.7884. Min Range: -1.7884

Max Act: 0.9498. Min Act: -0.0000

Data Index: 490913 (C4 (Web Text))

Max Activating Token Index: 432