Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 883 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.7081. Min Act: -0.0001

Data Index: 742165 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6901. Min Act: -0.0001

Data Index: 968399 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5956. Min Act: -0.0001

Data Index: 317779 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5436. Min Act: -0.0000

Data Index: 984046 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5437. Min Act: -0.0001

Data Index: 805812 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1236442 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5344. Min Act: -0.0001

Data Index: 429268 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5246. Min Act: -0.0000

Data Index: 377789 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4771. Min Act: -0.0001

Data Index: 717361 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4723. Min Act: -0.0001

Data Index: 401814 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4575. Min Act: -0.0000

Data Index: 719864 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4717. Min Act: -0.0001

Data Index: 747463 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4504. Min Act: -0.0001

Data Index: 399553 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4593. Min Act: -0.0001

Data Index: 1080400 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4438. Min Act: -0.0001

Data Index: 877141 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4743. Min Act: -0.0001

Data Index: 484414 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4267. Min Act: -0.0001

Data Index: 222463 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1028052 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4683. Min Act: -0.0001

Data Index: 929437 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.4417. Min Act: -0.0001

Data Index: 950177 (C4 (Web Text))

Max Activating Token Index: 748