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

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

Neuron 1233 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3005. Min Range: -5.3005

Max Act: 5.3005. Min Act: -0.0001

Data Index: 877370 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.8614. Min Act: -0.0001

Data Index: 713721 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.5255. Min Act: -0.0001

Data Index: 980568 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 5.3005. Min Range: -5.3005

Max Act: 5.0120. Min Act: -0.0001

Data Index: 1245896 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.9131. Min Act: -0.0001

Data Index: 456915 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.5437. Min Act: -0.0001

Data Index: 116011 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.5255. Min Act: -0.0001

Data Index: 797 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.6717. Min Act: -0.0001

Data Index: 1120752 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.2850. Min Act: -0.0001

Data Index: 182495 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.6337. Min Act: -0.0001

Data Index: 426134 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.4367. Min Act: -0.0001

Data Index: 1268346 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.7582. Min Act: -0.0001

Data Index: 53706 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.2417. Min Act: -0.0001

Data Index: 196460 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.3807. Min Act: -0.0001

Data Index: 601836 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.4969. Min Act: -0.0001

Data Index: 1149828 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.3439. Min Act: -0.0001

Data Index: 80311 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.1644. Min Act: -0.0001

Data Index: 1171659 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.4248. Min Act: -0.0001

Data Index: 32292 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.5540. Min Act: -0.0001

Data Index: 1094091 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 5.3005. Min Range: -5.3005

Max Act: 4.3769. Min Act: -0.0001

Data Index: 293568 (C4 (Web Text))

Max Activating Token Index: 100