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

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

Neuron 4592 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: 3.6584. Min Range: -3.6584

Max Act: 3.6584. Min Act: -0.0001

Data Index: 1402243 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 3.6584. Min Range: -3.6584

Max Act: 3.0559. Min Act: -0.0001

Data Index: 1360757 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.5129. Min Act: -0.0001

Data Index: 1201478 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.5872. Min Act: -0.0001

Data Index: 1060561 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.5024. Min Act: -0.0001

Data Index: 758225 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.3021. Min Act: -0.0001

Data Index: 343058 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.3985. Min Act: -0.0001

Data Index: 1242004 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.2569. Min Act: -0.0001

Data Index: 313191 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.3421. Min Act: -0.0001

Data Index: 1033558 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 3.6584. Min Range: -3.6584

Max Act: 1.9972. Min Act: -0.0001

Data Index: 1057924 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.2119. Min Act: -0.0001

Data Index: 944260 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.2845. Min Act: -0.0001

Data Index: 52774 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.1790. Min Act: -0.0001

Data Index: 737288 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.0689. Min Act: -0.0001

Data Index: 723876 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.2997. Min Act: -0.0001

Data Index: 5493 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.0742. Min Act: -0.0001

Data Index: 13655 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.1498. Min Act: -0.0001

Data Index: 700581 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.1486. Min Act: -0.0001

Data Index: 18817 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.1499. Min Act: -0.0001

Data Index: 968901 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 3.6584. Min Range: -3.6584

Max Act: 2.0192. Min Act: -0.0001

Data Index: 51792 (C4 (Web Text))

Max Activating Token Index: 274