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

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

Neuron 4690 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: 3.5419. Min Range: -3.5419

Max Act: 3.5419. Min Act: -0.0000

Data Index: 492128 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3070. Min Act: -0.0000

Data Index: 641825 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.1101. Min Act: -0.0001

Data Index: 965082 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.6239. Min Act: -0.0000

Data Index: 400160 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.0070. Min Act: -0.0001

Data Index: 577326 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.1691. Min Act: -0.0000

Data Index: 926972 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.0731. Min Act: -0.0000

Data Index: 491913 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2885. Min Act: -0.0000

Data Index: 1114788 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.8534. Min Act: -0.0000

Data Index: 523303 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.7446. Min Act: -0.0000

Data Index: 857106 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2662. Min Act: -0.0000

Data Index: 1146519 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.7984. Min Act: -0.0000

Data Index: 873064 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.9018. Min Act: -0.0000

Data Index: 794245 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.6401. Min Act: -0.0000

Data Index: 401905 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.0963. Min Act: -0.0001

Data Index: 1242112 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.4640. Min Act: -0.0000

Data Index: 278924 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.8375. Min Act: -0.0000

Data Index: 1044454 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.8079. Min Act: -0.0000

Data Index: 426749 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.9310. Min Act: -0.0000

Data Index: 136775 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 3.5419. Min Range: -3.5419

Max Act: 2.0900. Min Act: -0.0001

Data Index: 40944 (C4 (Web Text))

Max Activating Token Index: 864