Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1712. Min Range: -4.1712

Max Act: 4.1712. Min Act: -0.0000

Data Index: 616949 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7476. Min Act: -0.0000

Data Index: 654428 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.8833. Min Act: -0.0000

Data Index: 1352193 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7940. Min Act: -0.0000

Data Index: 622419 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7041. Min Act: -0.0000

Data Index: 1190003 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.8014. Min Act: -0.0000

Data Index: 191689 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.8023. Min Act: -0.0000

Data Index: 618863 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.9471. Min Act: -0.0000

Data Index: 511049 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.9399. Min Act: -0.0000

Data Index: 692619 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7781. Min Act: -0.0000

Data Index: 1237274 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6011. Min Act: -0.0000

Data Index: 681341 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7177. Min Act: -0.0000

Data Index: 1136033 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7518. Min Act: -0.0000

Data Index: 875147 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.8695. Min Act: -0.0000

Data Index: 41151 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.5202. Min Act: -0.0000

Data Index: 388155 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6150. Min Act: -0.0000

Data Index: 1258470 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6085. Min Act: -0.0000

Data Index: 171117 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.4318. Min Act: -0.0000

Data Index: 946919 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.4073. Min Act: -0.0000

Data Index: 668327 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.5492. Min Act: -0.0000

Data Index: 192617 (C4 (Web Text))

Max Activating Token Index: 52