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

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

Neuron 315 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4715. Min Act: -0.0000

Data Index: 568902 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4915. Min Act: -0.0000

Data Index: 78533 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3659. Min Act: -0.0000

Data Index: 282385 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3259. Min Act: -0.0000

Data Index: 653958 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1222087 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1016415 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1290108 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2967. Min Act: -0.0000

Data Index: 213949 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1331155 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1196328 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1235657 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2751. Min Act: -0.0000

Data Index: 735337 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2729. Min Act: -0.0000

Data Index: 858205 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2777. Min Act: -0.0000

Data Index: 98828 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2524. Min Act: -0.0000

Data Index: 454390 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2664. Min Act: -0.0000

Data Index: 719983 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1103329 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1425558 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2651. Min Act: -0.0000

Data Index: 742432 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.2571. Min Act: -0.0000

Data Index: 64491 (C4 (Web Text))

Max Activating Token Index: 1010