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

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

Neuron 3317 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1256950 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1113407 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1172529 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6052. Min Act: -0.0000

Data Index: 948339 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6402. Min Act: -0.0000

Data Index: 148903 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1121953 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5408. Min Act: -0.0000

Data Index: 136462 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1015721 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5532. Min Act: -0.0000

Data Index: 655397 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5339. Min Act: -0.0000

Data Index: 650148 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5323. Min Act: -0.0000

Data Index: 499058 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5016. Min Act: -0.0000

Data Index: 900405 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1109548 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1174845 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5067. Min Act: -0.0000

Data Index: 789357 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.4760. Min Act: -0.0000

Data Index: 507813 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.4709. Min Act: -0.0000

Data Index: 527895 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.4596. Min Act: -0.0000

Data Index: 733852 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1287331 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1092028 (C4 (Web Text))

Max Activating Token Index: 851