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

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

Neuron 970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.7465. Min Act: -0.0002

Data Index: 1021240 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5475. Min Act: -0.0002

Data Index: 783364 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.3555. Min Act: -0.0002

Data Index: 62563 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.2512. Min Act: -0.0002

Data Index: 76635 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.2725. Min Act: -0.0002

Data Index: 62806 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1589. Min Act: -0.0002

Data Index: 1025518 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.2239. Min Act: -0.0002

Data Index: 193454 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1395. Min Act: -0.0002

Data Index: 128108 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1650. Min Act: -0.0002

Data Index: 278997 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1944. Min Act: -0.0002

Data Index: 765698 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1114. Min Act: -0.0002

Data Index: 1132798 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1081. Min Act: -0.0002

Data Index: 190088 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1069. Min Act: -0.0002

Data Index: 1197387 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.0681. Min Act: -0.0002

Data Index: 914853 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1969. Min Act: -0.0002

Data Index: 979929 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1320. Min Act: -0.0002

Data Index: 1225526 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1224. Min Act: -0.0002

Data Index: 786760 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.0506. Min Act: -0.0002

Data Index: 529521 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1092. Min Act: -0.0002

Data Index: 774790 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.1087. Min Act: -0.0002

Data Index: 457937 (C4 (Web Text))

Max Activating Token Index: 401