Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.6086. Min Act: -0.0001

Data Index: 1490327 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1563339 (Python Code)

Max Activating Token Index: 355

Text #2

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4696. Min Act: -0.0001

Data Index: 1569262 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4626. Min Act: -0.0001

Data Index: 1506911 (Python Code)

Max Activating Token Index: 586

Text #4

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1400106 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1365947 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4374. Min Act: -0.0001

Data Index: 1494020 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4542. Min Act: -0.0001

Data Index: 1458438 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4381. Min Act: -0.0001

Data Index: 1518527 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1466085 (Python Code)

Max Activating Token Index: 140

Text #10

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1432906 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4040. Min Act: -0.0001

Data Index: 1519557 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1439602 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3902. Min Act: -0.0001

Data Index: 1508848 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3903. Min Act: -0.0001

Data Index: 1443055 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1644589 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3566. Min Act: -0.0001

Data Index: 1559011 (Python Code)

Max Activating Token Index: 256

Text #17

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1454050 (Python Code)

Max Activating Token Index: 669

Text #18

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3441. Min Act: -0.0001

Data Index: 1444017 (Python Code)

Max Activating Token Index: 493

Text #19

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3788. Min Act: -0.0001

Data Index: 1464148 (Python Code)

Max Activating Token Index: 862