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

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

Neuron 3511 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.5858. Min Act: -0.0001

Data Index: 155818 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.8321. Min Act: -0.0001

Data Index: 1609653 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6885. Min Act: -0.0001

Data Index: 842506 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.9100. Min Act: -0.0000

Data Index: 479127 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6478. Min Act: -0.0000

Data Index: 764804 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.5075. Min Act: -0.0000

Data Index: 1284671 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.2548. Min Act: -0.0000

Data Index: 62523 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.5192. Min Act: -0.0001

Data Index: 499729 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.3234. Min Act: -0.0000

Data Index: 864472 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.4183. Min Act: -0.0000

Data Index: 1279886 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.5725. Min Act: -0.0001

Data Index: 836734 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.3841. Min Act: -0.0000

Data Index: 887131 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.3957. Min Act: -0.0001

Data Index: 1556842 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.3524. Min Act: -0.0001

Data Index: 1641427 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.4550. Min Act: -0.0000

Data Index: 967764 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.4671. Min Act: -0.0001

Data Index: 722075 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.4542. Min Act: -0.0001

Data Index: 91730 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.3197. Min Act: -0.0000

Data Index: 835322 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.3253. Min Act: -0.0001

Data Index: 910802 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.4487. Min Act: -0.0000

Data Index: 991727 (C4 (Web Text))

Max Activating Token Index: 398