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

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

Neuron 5512 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.6181. Min Act: -0.0001

Data Index: 546686 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5759. Min Act: -0.0001

Data Index: 1335301 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5345. Min Act: -0.0001

Data Index: 665581 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4846. Min Act: -0.0001

Data Index: 1011167 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4834. Min Act: -0.0001

Data Index: 246818 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4499. Min Act: -0.0001

Data Index: 806929 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4618. Min Act: -0.0001

Data Index: 575975 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4605. Min Act: -0.0001

Data Index: 91800 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1039593 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4330. Min Act: -0.0001

Data Index: 503238 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4354. Min Act: -0.0001

Data Index: 155944 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4434. Min Act: -0.0001

Data Index: 546136 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4551. Min Act: -0.0001

Data Index: 295899 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4307. Min Act: -0.0001

Data Index: 20448 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4148. Min Act: -0.0001

Data Index: 696581 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.3976. Min Act: -0.0001

Data Index: 1086205 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4425. Min Act: -0.0001

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4381. Min Act: -0.0001

Data Index: 340220 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.3924. Min Act: -0.0001

Data Index: 502331 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4030. Min Act: -0.0001

Data Index: 54501 (C4 (Web Text))

Max Activating Token Index: 820