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

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

Neuron 572 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.5370. Min Act: -0.0000

Data Index: 375314 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4462. Min Act: -0.0000

Data Index: 739456 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4259. Min Act: -0.0000

Data Index: 163437 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4384. Min Act: -0.0000

Data Index: 490071 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4444. Min Act: -0.0000

Data Index: 808665 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4303. Min Act: -0.0000

Data Index: 624673 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1036753 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4089. Min Act: -0.0000

Data Index: 487183 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4217. Min Act: -0.0000

Data Index: 955046 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4026. Min Act: -0.0000

Data Index: 751345 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4133. Min Act: -0.0000

Data Index: 583426 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4075. Min Act: -0.0000

Data Index: 376131 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3954. Min Act: -0.0000

Data Index: 904741 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1306436 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3731. Min Act: -0.0000

Data Index: 788657 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1357257 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1035917 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1193465 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3714. Min Act: -0.0000

Data Index: 37437 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3846. Min Act: -0.0000

Data Index: 372876 (C4 (Web Text))

Max Activating Token Index: 328