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

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

Neuron 2719 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: 0.4787. Min Range: -0.4787

Max Act: 0.4787. Min Act: -0.0000

Data Index: 613607 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4356. Min Act: -0.0000

Data Index: 484924 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1041024 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4140. Min Act: -0.0000

Data Index: 666602 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3652. Min Act: -0.0000

Data Index: 452473 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1085139 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3743. Min Act: -0.0000

Data Index: 292824 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3646. Min Act: -0.0000

Data Index: 343780 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3730. Min Act: -0.0000

Data Index: 97832 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3607. Min Act: -0.0000

Data Index: 520619 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3954. Min Act: -0.0000

Data Index: 763494 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3605. Min Act: -0.0000

Data Index: 809964 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3628. Min Act: -0.0000

Data Index: 857229 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3580. Min Act: -0.0000

Data Index: 537211 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1162510 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3400. Min Act: -0.0000

Data Index: 744754 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3329. Min Act: -0.0000

Data Index: 108989 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3333. Min Act: -0.0000

Data Index: 602389 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3298. Min Act: -0.0000

Data Index: 602497 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1202474 (C4 (Web Text))

Max Activating Token Index: 850