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

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

Neuron 522 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: 0.3646. Min Range: -0.3646

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1188764 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1045766 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3205. Min Act: -0.0000

Data Index: 195005 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2992. Min Act: -0.0000

Data Index: 749826 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3049. Min Act: -0.0000

Data Index: 613866 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2977. Min Act: -0.0000

Data Index: 720467 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2826. Min Act: -0.0000

Data Index: 278334 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2543. Min Act: -0.0000

Data Index: 348097 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2859. Min Act: -0.0000

Data Index: 811431 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2617. Min Act: -0.0000

Data Index: 93479 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2835. Min Act: -0.0000

Data Index: 474026 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2561. Min Act: -0.0000

Data Index: 661239 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2683. Min Act: -0.0000

Data Index: 423493 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2486. Min Act: -0.0000

Data Index: 220227 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1414991 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2379. Min Act: -0.0000

Data Index: 650279 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2319. Min Act: -0.0000

Data Index: 823966 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2319. Min Act: -0.0000

Data Index: 806988 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1207295 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 816