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

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

Neuron 317 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: 1.7713. Min Range: -1.7713

Max Act: 1.7713. Min Act: -0.0000

Data Index: 863736 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1624102 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.6502. Min Act: -0.0000

Data Index: 101682 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.5110. Min Act: -0.0000

Data Index: 298671 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.6740. Min Act: -0.0000

Data Index: 604205 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.5486. Min Act: -0.0000

Data Index: 5195 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1383906 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4984. Min Act: -0.0000

Data Index: 471499 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.5009. Min Act: -0.0000

Data Index: 853496 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4153. Min Act: -0.0000

Data Index: 470005 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1512651 (Python Code)

Max Activating Token Index: 619

Text #11

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4172. Min Act: -0.0000

Data Index: 427254 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4922. Min Act: -0.0000

Data Index: 151963 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1399482 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1305456 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.4977. Min Act: -0.0000

Data Index: 430038 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.3957. Min Act: -0.0000

Data Index: 507041 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.5629. Min Act: -0.0000

Data Index: 1020825 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.2865. Min Act: -0.0000

Data Index: 1642729 (Python Code)

Max Activating Token Index: 153

Text #19

Max Range: 1.7713. Min Range: -1.7713

Max Act: 1.3376. Min Act: -0.0000

Data Index: 341620 (C4 (Web Text))

Max Activating Token Index: 401