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

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

Neuron 4737 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1752. Min Range: -6.1752

Max Act: 6.1752. Min Act: -0.0000

Data Index: 1168543 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.9582. Min Act: -0.0000

Data Index: 275897 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.7295. Min Act: -0.0000

Data Index: 945976 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.8091. Min Act: -0.0000

Data Index: 665174 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.9411. Min Act: -0.0000

Data Index: 631352 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.6286. Min Act: -0.0000

Data Index: 1156890 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.4897. Min Act: -0.0000

Data Index: 1283974 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.4890. Min Act: -0.0000

Data Index: 610326 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 6.1752. Min Range: -6.1752

Max Act: 3.9985. Min Act: -0.0000

Data Index: 587083 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.1632. Min Act: -0.0000

Data Index: 832076 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.0815. Min Act: -0.0000

Data Index: 979481 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.0501. Min Act: -0.0000

Data Index: 1038820 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 6.1752. Min Range: -6.1752

Max Act: 3.8393. Min Act: -0.0000

Data Index: 1012514 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.0292. Min Act: -0.0000

Data Index: 86782 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 6.1752. Min Range: -6.1752

Max Act: 3.9296. Min Act: -0.0000

Data Index: 514936 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 6.1752. Min Range: -6.1752

Max Act: 3.7429. Min Act: -0.0001

Data Index: 1058236 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 6.1752. Min Range: -6.1752

Max Act: 4.0713. Min Act: -0.0000

Data Index: 402174 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 6.1752. Min Range: -6.1752

Max Act: 3.5194. Min Act: -0.0000

Data Index: 344240 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 6.1752. Min Range: -6.1752

Max Act: 3.5202. Min Act: -0.0000

Data Index: 545664 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 6.1752. Min Range: -6.1752

Max Act: 3.4764. Min Act: -0.0000

Data Index: 844848 (C4 (Web Text))

Max Activating Token Index: 33