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

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

Neuron 5134 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.8162. Min Act: -0.0000

Data Index: 159334 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.7099. Min Act: -0.0000

Data Index: 963607 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.6579. Min Act: -0.0000

Data Index: 1290887 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.5736. Min Act: -0.0000

Data Index: 393164 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.5487. Min Act: -0.0000

Data Index: 520582 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.2284. Min Act: -0.0000

Data Index: 517197 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.3606. Min Act: -0.0000

Data Index: 704382 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.5594. Min Act: -0.0000

Data Index: 476609 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.3145. Min Act: -0.0000

Data Index: 1173122 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 5.8162. Min Range: -5.8162

Max Act: 4.9418. Min Act: -0.0000

Data Index: 30941 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.4420. Min Act: -0.0000

Data Index: 697095 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.1832. Min Act: -0.0000

Data Index: 1196007 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 5.8162. Min Range: -5.8162

Max Act: 4.8769. Min Act: -0.0000

Data Index: 1054984 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 5.8162. Min Range: -5.8162

Max Act: 5.0166. Min Act: -0.0000

Data Index: 791964 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 5.8162. Min Range: -5.8162

Max Act: 4.5592. Min Act: -0.0000

Data Index: 431385 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 5.8162. Min Range: -5.8162

Max Act: 4.4861. Min Act: -0.0000

Data Index: 274362 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.8162. Min Range: -5.8162

Max Act: 4.3583. Min Act: -0.0000

Data Index: 97635 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 5.8162. Min Range: -5.8162

Max Act: 4.1546. Min Act: -0.0000

Data Index: 529168 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 5.8162. Min Range: -5.8162

Max Act: 3.6769. Min Act: -0.0000

Data Index: 465100 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 5.8162. Min Range: -5.8162

Max Act: 4.1058. Min Act: -0.0000

Data Index: 909122 (C4 (Web Text))

Max Activating Token Index: 761