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

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

Neuron 4892 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: 2.2045. Min Range: -2.2045

Max Act: 2.2045. Min Act: -0.0000

Data Index: 1480221 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.6580. Min Act: -0.0000

Data Index: 1539554 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1509648 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1511083 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1462448 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1400725 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1606133 (Python Code)

Max Activating Token Index: 413

Text #7

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.3322. Min Act: -0.0000

Data Index: 1624666 (Python Code)

Max Activating Token Index: 427

Text #8

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1573049 (Python Code)

Max Activating Token Index: 276

Text #9

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.2580. Min Act: -0.0000

Data Index: 1484572 (Python Code)

Max Activating Token Index: 522

Text #10

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.2862. Min Act: -0.0000

Data Index: 1200087 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.2433. Min Act: -0.0000

Data Index: 634644 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.2407. Min Act: -0.0000

Data Index: 1414440 (Python Code)

Max Activating Token Index: 375

Text #13

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1429798 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.1990. Min Act: -0.0000

Data Index: 365553 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1577470 (Python Code)

Max Activating Token Index: 103

Text #16

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1420498 (Python Code)

Max Activating Token Index: 266

Text #17

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1566323 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1373816 (Python Code)

Max Activating Token Index: 277

Text #19

Max Range: 2.2045. Min Range: -2.2045

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1465748 (Python Code)

Max Activating Token Index: 141