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

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

Neuron 4458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3943. Min Range: -5.3943

Max Act: 5.3455. Min Act: -0.0000

Data Index: 77424 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 5.3943. Min Range: -5.3943

Max Act: 5.3943. Min Act: -0.0000

Data Index: 983992 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 5.3943. Min Range: -5.3943

Max Act: 5.2653. Min Act: -0.0000

Data Index: 1040014 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.7207. Min Act: -0.0000

Data Index: 695500 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.6172. Min Act: -0.0000

Data Index: 190436 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.1114. Min Act: -0.0000

Data Index: 766255 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.2835. Min Act: -0.0000

Data Index: 1197583 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.2086. Min Act: -0.0000

Data Index: 603044 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.1159. Min Act: -0.0000

Data Index: 1351120 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.2182. Min Act: -0.0000

Data Index: 918426 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.1564. Min Act: -0.0000

Data Index: 776814 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.1346. Min Act: -0.0000

Data Index: 678032 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.3155. Min Act: -0.0000

Data Index: 161745 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.0400. Min Act: -0.0000

Data Index: 448521 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.1132. Min Act: -0.0000

Data Index: 501621 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.0745. Min Act: -0.0000

Data Index: 1278289 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.2294. Min Act: -0.0000

Data Index: 780366 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 5.3943. Min Range: -5.3943

Max Act: 3.9692. Min Act: -0.0000

Data Index: 725612 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 5.3943. Min Range: -5.3943

Max Act: 3.8220. Min Act: -0.0000

Data Index: 803412 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 5.3943. Min Range: -5.3943

Max Act: 4.0025. Min Act: -0.0000

Data Index: 792810 (C4 (Web Text))

Max Activating Token Index: 804