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

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

Neuron 2591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1740. Min Range: -2.1740

Max Act: 2.1740. Min Act: -0.0000

Data Index: 1298390 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 2.1740. Min Range: -2.1740

Max Act: 2.0050. Min Act: -0.0000

Data Index: 994383 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.7010. Min Act: -0.0000

Data Index: 133485 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.7635. Min Act: -0.0000

Data Index: 710433 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.7211. Min Act: -0.0000

Data Index: 983581 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1273950 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.6901. Min Act: -0.0000

Data Index: 1221138 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.5636. Min Act: -0.0000

Data Index: 230154 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.7490. Min Act: -0.0000

Data Index: 979050 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.6319. Min Act: -0.0000

Data Index: 847192 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.5843. Min Act: -0.0000

Data Index: 491730 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.4933. Min Act: -0.0000

Data Index: 186100 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.5543. Min Act: -0.0000

Data Index: 774758 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.6256. Min Act: -0.0000

Data Index: 255128 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.5247. Min Act: -0.0000

Data Index: 1221499 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.5224. Min Act: -0.0000

Data Index: 371904 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.5226. Min Act: -0.0000

Data Index: 195504 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.5901. Min Act: -0.0000

Data Index: 1174217 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.4488. Min Act: -0.0000

Data Index: 1066661 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 2.1740. Min Range: -2.1740

Max Act: 1.3319. Min Act: -0.0000

Data Index: 601832 (C4 (Web Text))

Max Activating Token Index: 821