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

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

Neuron 3718 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1208504 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5743. Min Act: -0.0000

Data Index: 246593 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5327. Min Act: -0.0000

Data Index: 432116 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5445. Min Act: -0.0000

Data Index: 922117 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1287592 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5086. Min Act: -0.0000

Data Index: 293436 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5402. Min Act: -0.0000

Data Index: 475 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4846. Min Act: -0.0000

Data Index: 923935 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1118393 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5258. Min Act: -0.0000

Data Index: 841809 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5121. Min Act: -0.0000

Data Index: 864544 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5087. Min Act: -0.0000

Data Index: 137265 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1012826 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4793. Min Act: -0.0000

Data Index: 435275 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4820. Min Act: -0.0000

Data Index: 151798 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4748. Min Act: -0.0000

Data Index: 757332 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4703. Min Act: -0.0000

Data Index: 677412 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1164095 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4165. Min Act: -0.0000

Data Index: 454084 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4593. Min Act: -0.0000

Data Index: 25723 (C4 (Web Text))

Max Activating Token Index: 114