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

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

Neuron 1811 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: 1.3401. Min Range: -1.3401

Max Act: 1.3401. Min Act: -0.0000

Data Index: 444924 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1293646 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.2670. Min Act: -0.0000

Data Index: 683539 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1095554 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1074904 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 1.3401. Min Range: -1.3401

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1299511 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.8375. Min Act: -0.0000

Data Index: 487261 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.7606. Min Act: -0.0000

Data Index: 54486 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1305154 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.7558. Min Act: -0.0000

Data Index: 937007 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1268754 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.7419. Min Act: -0.0000

Data Index: 107141 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.7585. Min Act: -0.0000

Data Index: 982128 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1580579 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1101652 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.6494. Min Act: -0.0000

Data Index: 46530 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.5649. Min Act: -0.0000

Data Index: 545594 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.6233. Min Act: -0.0000

Data Index: 198207 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1480341 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 1.3401. Min Range: -1.3401

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1645892 (Python Code)

Max Activating Token Index: 110