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

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

Neuron 1513 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: 0.4495. Min Range: -0.4495

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1462599 (Python Code)

Max Activating Token Index: 591

Text #1

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1457954 (Python Code)

Max Activating Token Index: 730

Text #2

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1610274 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2596. Min Act: -0.0000

Data Index: 216272 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3174. Min Act: -0.0000

Data Index: 429182 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1525835 (Python Code)

Max Activating Token Index: 458

Text #6

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1060620 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1408390 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1403606 (Python Code)

Max Activating Token Index: 197

Text #9

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2578. Min Act: -0.0000

Data Index: 142481 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2730. Min Act: -0.0000

Data Index: 335939 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1200115 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1426576 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2793. Min Act: -0.0000

Data Index: 634487 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2542. Min Act: -0.0000

Data Index: 252452 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2846. Min Act: -0.0000

Data Index: 938824 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1625033 (Python Code)

Max Activating Token Index: 986

Text #17

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1114831 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2472. Min Act: -0.0000

Data Index: 27405 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2441. Min Act: -0.0000

Data Index: 879278 (C4 (Web Text))

Max Activating Token Index: 920