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

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

Neuron 1350 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: 1.7530. Min Range: -1.7530

Max Act: 1.7530. Min Act: -0.0000

Data Index: 762203 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.5702. Min Act: -0.0000

Data Index: 1035664 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.5637. Min Act: -0.0000

Data Index: 791543 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.5061. Min Act: -0.0000

Data Index: 675493 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1214446 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.4026. Min Act: -0.0000

Data Index: 540318 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.4530. Min Act: -0.0000

Data Index: 310917 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.4651. Min Act: -0.0000

Data Index: 262996 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.4447. Min Act: -0.0000

Data Index: 774557 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.4465. Min Act: -0.0000

Data Index: 570508 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.4412. Min Act: -0.0000

Data Index: 1132682 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.4456. Min Act: -0.0000

Data Index: 597814 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3911. Min Act: -0.0000

Data Index: 1296304 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1332257 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3432. Min Act: -0.0000

Data Index: 969279 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3186. Min Act: -0.0000

Data Index: 532379 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.2493. Min Act: -0.0000

Data Index: 259640 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3165. Min Act: -0.0000

Data Index: 779452 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3745. Min Act: -0.0000

Data Index: 39935 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 1.7530. Min Range: -1.7530

Max Act: 1.3019. Min Act: -0.0000

Data Index: 207675 (C4 (Web Text))

Max Activating Token Index: 700