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

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

Neuron 1803 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: 2.9858. Min Range: -2.9858

Max Act: 2.9619. Min Act: -0.0000

Data Index: 208497 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.9858. Min Act: -0.0000

Data Index: 1145236 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.6055. Min Act: -0.0000

Data Index: 1298123 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.7263. Min Act: -0.0000

Data Index: 677147 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.3779. Min Act: -0.0000

Data Index: 23226 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.2920. Min Act: -0.0000

Data Index: 866362 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.0832. Min Act: -0.0000

Data Index: 1099484 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.2670. Min Act: -0.0000

Data Index: 175498 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.1434. Min Act: -0.0000

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.2472. Min Act: -0.0000

Data Index: 271596 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.1778. Min Act: -0.0000

Data Index: 427198 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.0407. Min Act: -0.0000

Data Index: 279416 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 2.9858. Min Range: -2.9858

Max Act: 1.8120. Min Act: -0.0000

Data Index: 615141 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 2.9858. Min Range: -2.9858

Max Act: 1.9830. Min Act: -0.0000

Data Index: 96944 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.0941. Min Act: -0.0000

Data Index: 136195 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 2.9858. Min Range: -2.9858

Max Act: 1.7743. Min Act: -0.0000

Data Index: 897440 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.1936. Min Act: -0.0000

Data Index: 202235 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.0846. Min Act: -0.0000

Data Index: 1176493 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 2.9858. Min Range: -2.9858

Max Act: 2.0690. Min Act: -0.0000

Data Index: 513276 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 2.9858. Min Range: -2.9858

Max Act: 1.9388. Min Act: -0.0000

Data Index: 885222 (C4 (Web Text))

Max Activating Token Index: 695