Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 532 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.5440. Min Act: -0.0001

Data Index: 482748 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.5446. Min Act: -0.0001

Data Index: 820621 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.5212. Min Act: -0.0001

Data Index: 1210833 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4723. Min Act: -0.0001

Data Index: 837582 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.5099. Min Act: -0.0001

Data Index: 869026 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4457. Min Act: -0.0001

Data Index: 476858 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4675. Min Act: -0.0001

Data Index: 753362 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4534. Min Act: -0.0001

Data Index: 326310 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4562. Min Act: -0.0001

Data Index: 673303 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4356. Min Act: -0.0001

Data Index: 66860 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4149. Min Act: -0.0000

Data Index: 762058 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4237. Min Act: -0.0001

Data Index: 1282312 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4371. Min Act: -0.0001

Data Index: 1334438 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4156. Min Act: -0.0001

Data Index: 1301658 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3877. Min Act: -0.0001

Data Index: 674343 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1120756 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3930. Min Act: -0.0001

Data Index: 991932 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4118. Min Act: -0.0001

Data Index: 97833 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3472. Min Act: -0.0001

Data Index: 1220149 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3783. Min Act: -0.0001

Data Index: 866605 (C4 (Web Text))

Max Activating Token Index: 107