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

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

Neuron 5305 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2079. Min Range: -4.2079

Max Act: 4.2079. Min Act: -0.0000

Data Index: 690871 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 4.2079. Min Range: -4.2079

Max Act: 3.6273. Min Act: -0.0000

Data Index: 839774 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 4.2079. Min Range: -4.2079

Max Act: 3.2899. Min Act: -0.0000

Data Index: 22488 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.6847. Min Act: -0.0000

Data Index: 922764 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.4606. Min Act: -0.0000

Data Index: 73494 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.5747. Min Act: -0.0000

Data Index: 1106577 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.4184. Min Act: -0.0000

Data Index: 341184 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.5670. Min Act: -0.0000

Data Index: 163552 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.5252. Min Act: -0.0000

Data Index: 411111 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.5160. Min Act: -0.0000

Data Index: 593360 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.4865. Min Act: -0.0000

Data Index: 1326288 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.6030. Min Act: -0.0000

Data Index: 113295 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.4559. Min Act: -0.0000

Data Index: 344218 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.4527. Min Act: -0.0000

Data Index: 131724 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.4402. Min Act: -0.0000

Data Index: 1308904 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.4562. Min Act: -0.0000

Data Index: 68921 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.5529. Min Act: -0.0000

Data Index: 404436 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.3789. Min Act: -0.0000

Data Index: 800239 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.2760. Min Act: -0.0000

Data Index: 422578 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 4.2079. Min Range: -4.2079

Max Act: 2.3982. Min Act: -0.0000

Data Index: 991564 (C4 (Web Text))

Max Activating Token Index: 986