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

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

Neuron 2818 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: 1.1155. Min Range: -1.1155

Max Act: 1.1155. Min Act: -0.0000

Data Index: 543546 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.1155. Min Range: -1.1155

Max Act: 1.0081. Min Act: -0.0000

Data Index: 944470 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9401. Min Act: -0.0000

Data Index: 705405 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1207604 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9093. Min Act: -0.0000

Data Index: 330163 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1103999 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1332862 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8974. Min Act: -0.0000

Data Index: 619534 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8970. Min Act: -0.0000

Data Index: 516223 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8862. Min Act: -0.0000

Data Index: 52626 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8797. Min Act: -0.0000

Data Index: 982170 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9048. Min Act: -0.0000

Data Index: 446245 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1299399 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1312554 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1345771 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1262148 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8512. Min Act: -0.0000

Data Index: 886315 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8384. Min Act: 0.0000

Data Index: 151262 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1090320 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8291. Min Act: -0.0000

Data Index: 778337 (C4 (Web Text))

Max Activating Token Index: 455