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

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

Neuron 5285 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.9782. Min Act: -0.0000

Data Index: 675782 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.6304. Min Act: -0.0000

Data Index: 663284 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.5362. Min Act: -0.0000

Data Index: 895818 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.2659. Min Act: -0.0000

Data Index: 99146 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.3659. Min Act: -0.0000

Data Index: 759363 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.2047. Min Act: -0.0000

Data Index: 1159232 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.1562. Min Act: -0.0000

Data Index: 740662 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.0411. Min Act: -0.0000

Data Index: 1089439 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.1075. Min Act: -0.0000

Data Index: 410718 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.1647. Min Act: -0.0000

Data Index: 754844 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.1450. Min Act: -0.0000

Data Index: 1055035 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.1311. Min Act: -0.0000

Data Index: 311329 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.0155. Min Act: -0.0000

Data Index: 1249952 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.9782. Min Range: -2.9782

Max Act: 1.9974. Min Act: -0.0000

Data Index: 248329 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 2.9782. Min Range: -2.9782

Max Act: 1.9942. Min Act: -0.0000

Data Index: 112847 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 2.9782. Min Range: -2.9782

Max Act: 1.9835. Min Act: -0.0000

Data Index: 1146321 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 2.9782. Min Range: -2.9782

Max Act: 2.0479. Min Act: -0.0000

Data Index: 1151463 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 2.9782. Min Range: -2.9782

Max Act: 1.9364. Min Act: -0.0000

Data Index: 77855 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 2.9782. Min Range: -2.9782

Max Act: 1.8163. Min Act: -0.0000

Data Index: 881183 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 2.9782. Min Range: -2.9782

Max Act: 1.9256. Min Act: -0.0000

Data Index: 889705 (C4 (Web Text))

Max Activating Token Index: 1022