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

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

Neuron 1514 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.3297. Min Act: -0.0001

Data Index: 938292 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.1982. Min Act: -0.0001

Data Index: 1336464 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.1144. Min Act: -0.0001

Data Index: 65002 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.0465. Min Act: -0.0001

Data Index: 411739 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.0495. Min Act: -0.0001

Data Index: 358864 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.0150. Min Act: -0.0001

Data Index: 725232 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.0878. Min Act: -0.0001

Data Index: 885170 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9817. Min Act: -0.0001

Data Index: 926570 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9261. Min Act: -0.0001

Data Index: 291970 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9405. Min Act: -0.0001

Data Index: 716413 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8017. Min Act: -0.0001

Data Index: 1032857 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7763. Min Act: -0.0001

Data Index: 1203867 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8986. Min Act: -0.0001

Data Index: 325005 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1253638 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9179. Min Act: -0.0001

Data Index: 189192 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8910. Min Act: -0.0001

Data Index: 331289 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8357. Min Act: -0.0001

Data Index: 898255 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9337. Min Act: -0.0001

Data Index: 1336468 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1290834 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8487. Min Act: -0.0001

Data Index: 1212555 (C4 (Web Text))

Max Activating Token Index: 1006