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

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

Neuron 4984 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1522166 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1532439 (Python Code)

Max Activating Token Index: 576

Text #2

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8113. Min Act: -0.0000

Data Index: 703368 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1577216 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1097964 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1543494 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7190. Min Act: -0.0000

Data Index: 778963 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.6398. Min Act: -0.0000

Data Index: 208338 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1482810 (Python Code)

Max Activating Token Index: 217

Text #9

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1444669 (Python Code)

Max Activating Token Index: 994

Text #10

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1363681 (Python Code)

Max Activating Token Index: 736

Text #11

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1489381 (Python Code)

Max Activating Token Index: 980

Text #12

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.5905. Min Act: -0.0000

Data Index: 792287 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1621900 (Python Code)

Max Activating Token Index: 175

Text #14

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.5637. Min Act: -0.0000

Data Index: 787517 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.5806. Min Act: -0.0000

Data Index: 733283 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1105160 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1183864 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.5625. Min Act: -0.0000

Data Index: 926410 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.5355. Min Act: -0.0000

Data Index: 484676 (C4 (Web Text))

Max Activating Token Index: 973