Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5158 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.4593. Min Range: -5.4593

Max Act: 5.3676. Min Act: -0.0000

Data Index: 184363 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 5.4593. Min Range: -5.4593

Max Act: 5.4371. Min Act: -0.0000

Data Index: 827544 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 5.4593. Min Range: -5.4593

Max Act: 5.3646. Min Act: -0.0000

Data Index: 737111 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 5.4593. Min Range: -5.4593

Max Act: 5.1655. Min Act: -0.0000

Data Index: 36324 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.9430. Min Act: -0.0000

Data Index: 371060 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 5.4593. Min Range: -5.4593

Max Act: 5.4593. Min Act: -0.0000

Data Index: 545607 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.9756. Min Act: -0.0000

Data Index: 908068 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 5.4593. Min Range: -5.4593

Max Act: 5.2232. Min Act: -0.0000

Data Index: 933874 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.5290. Min Act: -0.0000

Data Index: 758010 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.7477. Min Act: -0.0000

Data Index: 1078749 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.8574. Min Act: -0.0000

Data Index: 1108562 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.6924. Min Act: -0.0000

Data Index: 397629 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.6141. Min Act: -0.0000

Data Index: 1229025 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.3080. Min Act: -0.0000

Data Index: 1015344 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.4480. Min Act: -0.0000

Data Index: 417518 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.4200. Min Act: -0.0000

Data Index: 1068735 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.3321. Min Act: -0.0000

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 5.4593. Min Range: -5.4593

Max Act: 3.9285. Min Act: -0.0000

Data Index: 1120916 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.3837. Min Act: -0.0000

Data Index: 143173 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 5.4593. Min Range: -5.4593

Max Act: 4.3235. Min Act: -0.0000

Data Index: 867947 (C4 (Web Text))

Max Activating Token Index: 156