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

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

Neuron 1128 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0140. Min Range: -1.0140

Max Act: 1.0140. Min Act: -0.0000

Data Index: 455141 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8430. Min Act: -0.0000

Data Index: 498518 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7900. Min Act: 0.0001

Data Index: 857836 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1186846 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1186886 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7793. Min Act: -0.0000

Data Index: 796360 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7316. Min Act: -0.0000

Data Index: 233430 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6751. Min Act: -0.0000

Data Index: 37790 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6924. Min Act: -0.0000

Data Index: 619598 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1355443 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6847. Min Act: -0.0000

Data Index: 334608 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6102. Min Act: -0.0000

Data Index: 604760 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1145236 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1090618 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6410. Min Act: -0.0000

Data Index: 999990 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6658. Min Act: -0.0000

Data Index: 40867 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1034227 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6296. Min Act: -0.0000

Data Index: 695833 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6205. Min Act: -0.0000

Data Index: 709369 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6220. Min Act: -0.0000

Data Index: 900805 (C4 (Web Text))

Max Activating Token Index: 115