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

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

Neuron 3489 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: 1.1933. Min Range: -1.1933

Max Act: 1.1933. Min Act: -0.0001

Data Index: 14911 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1434. Min Act: -0.0001

Data Index: 882264 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0832. Min Act: -0.0001

Data Index: 313592 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1323. Min Act: -0.0001

Data Index: 499916 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0105. Min Act: -0.0001

Data Index: 74428 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0678. Min Act: -0.0001

Data Index: 311247 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0447. Min Act: -0.0001

Data Index: 365864 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0444. Min Act: -0.0001

Data Index: 804125 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1218462 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9679. Min Act: -0.0001

Data Index: 1377577 (Python Code)

Max Activating Token Index: 160

Text #10

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9743. Min Act: -0.0001

Data Index: 945755 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1569313 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9224. Min Act: -0.0001

Data Index: 1602452 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9166. Min Act: -0.0001

Data Index: 754210 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9154. Min Act: -0.0001

Data Index: 1545920 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1353556 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9102. Min Act: -0.0001

Data Index: 1355593 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8765. Min Act: -0.0001

Data Index: 4568 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9073. Min Act: -0.0001

Data Index: 1554382 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8998. Min Act: -0.0001

Data Index: 103810 (C4 (Web Text))

Max Activating Token Index: 807