Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 651 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0000

Data Index: 139045 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1099630 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0881. Min Act: -0.0000

Data Index: 512261 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0800. Min Act: -0.0001

Data Index: 211635 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0916. Min Act: -0.0000

Data Index: 462185 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0855. Min Act: -0.0001

Data Index: 132482 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1143750 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0834. Min Act: -0.0001

Data Index: 429846 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1216284 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1222222 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0786. Min Act: -0.0001

Data Index: 67092 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0808. Min Act: -0.0001

Data Index: 942730 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0755. Min Act: -0.0001

Data Index: 577389 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0743. Min Act: -0.0001

Data Index: 919216 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0703. Min Act: -0.0000

Data Index: 712566 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0755. Min Act: -0.0001

Data Index: 981593 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1327277 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0741. Min Act: -0.0001

Data Index: 626290 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1178736 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0724. Min Act: -0.0001

Data Index: 90710 (C4 (Web Text))

Max Activating Token Index: 416