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

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

Neuron 1596 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: 3.7412. Min Range: -3.7412

Max Act: 3.7412. Min Act: -0.0000

Data Index: 443319 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.5375. Min Act: -0.0000

Data Index: 541735 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.0421. Min Act: -0.0000

Data Index: 940069 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.0381. Min Act: -0.0000

Data Index: 879297 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.0037. Min Act: -0.0000

Data Index: 875248 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.9285. Min Act: -0.0000

Data Index: 235493 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.0174. Min Act: -0.0000

Data Index: 1234475 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.9318. Min Act: -0.0000

Data Index: 218362 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.6726. Min Act: -0.0000

Data Index: 980315 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.9134. Min Act: -0.0000

Data Index: 359680 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.5757. Min Act: -0.0000

Data Index: 726425 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.6588. Min Act: -0.0000

Data Index: 457969 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.7765. Min Act: -0.0000

Data Index: 162834 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.1703. Min Act: -0.0000

Data Index: 342083 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.1393. Min Act: -0.0000

Data Index: 295594 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.3681. Min Act: -0.0000

Data Index: 976280 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.5844. Min Act: -0.0000

Data Index: 1196968 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.4338. Min Act: -0.0000

Data Index: 171608 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 3.7412. Min Range: -3.7412

Max Act: 2.5270. Min Act: -0.0000

Data Index: 623775 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 3.7412. Min Range: -3.7412

Max Act: 1.7207. Min Act: -0.0000

Data Index: 580216 (C4 (Web Text))

Max Activating Token Index: 738