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

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

Neuron 1604 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.2861. Min Act: -0.0002

Data Index: 593991 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.2745. Min Act: -0.0001

Data Index: 207546 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.1784. Min Act: -0.0002

Data Index: 291505 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.1772. Min Act: -0.0002

Data Index: 523763 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.1424. Min Act: -0.0001

Data Index: 1194979 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0506. Min Act: -0.0002

Data Index: 768852 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0855. Min Act: -0.0001

Data Index: 1097392 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0333. Min Act: -0.0002

Data Index: 126762 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0096. Min Act: -0.0002

Data Index: 521508 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.1116. Min Act: -0.0001

Data Index: 1098892 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9753. Min Act: -0.0002

Data Index: 1196115 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0241. Min Act: -0.0002

Data Index: 873137 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0215. Min Act: -0.0002

Data Index: 748616 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0004. Min Act: -0.0002

Data Index: 167178 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9153. Min Act: -0.0002

Data Index: 626478 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8752. Min Act: -0.0002

Data Index: 1124476 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9663. Min Act: -0.0001

Data Index: 1045821 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9426. Min Act: -0.0002

Data Index: 930089 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9100. Min Act: -0.0002

Data Index: 757091 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9215. Min Act: -0.0002

Data Index: 1256026 (C4 (Web Text))

Max Activating Token Index: 315