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

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

Neuron 3208 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: 1.9044. Min Range: -1.9044

Max Act: 1.9044. Min Act: -0.0000

Data Index: 843140 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.7060. Min Act: -0.0000

Data Index: 1155992 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1154296 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1151223 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.6373. Min Act: -0.0000

Data Index: 18188 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5004. Min Act: -0.0000

Data Index: 913677 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1113468 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4766. Min Act: -0.0000

Data Index: 624450 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.5275. Min Act: -0.0000

Data Index: 895547 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1058544 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3131. Min Act: -0.0000

Data Index: 79352 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3432. Min Act: -0.0000

Data Index: 165960 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3897. Min Act: -0.0000

Data Index: 439265 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3477. Min Act: -0.0000

Data Index: 1091221 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1321263 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3356. Min Act: -0.0000

Data Index: 101433 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3777. Min Act: -0.0000

Data Index: 537769 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3500. Min Act: -0.0000

Data Index: 351433 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.4158. Min Act: -0.0000

Data Index: 626880 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.9044. Min Range: -1.9044

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1288383 (C4 (Web Text))

Max Activating Token Index: 134