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

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

Neuron 1677 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: 0.4685. Min Range: -0.4685

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1286553 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1171721 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1159625 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1268699 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3832. Min Act: -0.0000

Data Index: 348116 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3716. Min Act: -0.0000

Data Index: 694368 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1252389 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1180286 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3656. Min Act: -0.0000

Data Index: 180834 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3395. Min Act: -0.0000

Data Index: 488912 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3631. Min Act: -0.0000

Data Index: 943861 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3488. Min Act: -0.0000

Data Index: 247603 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3596. Min Act: -0.0000

Data Index: 128228 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1142692 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1200365 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3640. Min Act: -0.0000

Data Index: 335331 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1124205 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3600. Min Act: -0.0000

Data Index: 658962 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3339. Min Act: -0.0000

Data Index: 605191 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1216165 (C4 (Web Text))

Max Activating Token Index: 256