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

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

Neuron 2338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.7587. Min Act: -0.0001

Data Index: 1602677 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.7422. Min Act: -0.0000

Data Index: 336300 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.7235. Min Act: -0.0000

Data Index: 738200 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6990. Min Act: -0.0000

Data Index: 760165 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.7320. Min Act: -0.0000

Data Index: 173675 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6811. Min Act: -0.0000

Data Index: 32983 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6826. Min Act: -0.0000

Data Index: 761548 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6283. Min Act: -0.0001

Data Index: 1502020 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6237. Min Act: -0.0000

Data Index: 920868 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1484775 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6363. Min Act: -0.0000

Data Index: 550554 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.5955. Min Act: -0.0000

Data Index: 329288 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6324. Min Act: -0.0000

Data Index: 868442 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6477. Min Act: -0.0001

Data Index: 1506930 (Python Code)

Max Activating Token Index: 869

Text #14

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1529116 (Python Code)

Max Activating Token Index: 975

Text #15

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6056. Min Act: -0.0000

Data Index: 894666 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.5858. Min Act: -0.0000

Data Index: 414369 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1567958 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.6178. Min Act: -0.0000

Data Index: 358134 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.7587. Min Range: -0.7587

Max Act: 0.5808. Min Act: -0.0001

Data Index: 569261 (C4 (Web Text))

Max Activating Token Index: 10