Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5406 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.8845. Min Act: -0.0000

Data Index: 1549541 (Python Code)

Max Activating Token Index: 70

Text #1

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1317081 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6297. Min Act: -0.0000

Data Index: 766185 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6433. Min Act: -0.0000

Data Index: 39945 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6039. Min Act: -0.0000

Data Index: 185177 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.6007. Min Act: -0.0000

Data Index: 398488 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1426785 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1404153 (Python Code)

Max Activating Token Index: 753

Text #8

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1649198 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1188144 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5494. Min Act: -0.0000

Data Index: 673657 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5493. Min Act: -0.0000

Data Index: 631472 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1466936 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1626163 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5541. Min Act: -0.0000

Data Index: 214126 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5524. Min Act: -0.0000

Data Index: 267052 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1468602 (Python Code)

Max Activating Token Index: 318

Text #17

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1633053 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5309. Min Act: -0.0000

Data Index: 14831 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.8845. Min Range: -0.8845

Max Act: 0.5145. Min Act: -0.0000

Data Index: 804288 (C4 (Web Text))

Max Activating Token Index: 711