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

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

Neuron 5855 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5624. Min Act: -0.0001

Data Index: 439006 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1407238 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5342. Min Act: -0.0001

Data Index: 157781 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5271. Min Act: -0.0001

Data Index: 194308 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5190. Min Act: -0.0001

Data Index: 390641 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5086. Min Act: -0.0002

Data Index: 738510 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4955. Min Act: -0.0001

Data Index: 1634466 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4994. Min Act: -0.0001

Data Index: 1141894 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4908. Min Act: -0.0001

Data Index: 1603526 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4782. Min Act: -0.0001

Data Index: 1106780 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4797. Min Act: -0.0001

Data Index: 1573266 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4797. Min Act: -0.0001

Data Index: 1292147 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4725. Min Act: -0.0001

Data Index: 1536055 (Python Code)

Max Activating Token Index: 72

Text #13

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4699. Min Act: -0.0001

Data Index: 1414015 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4764. Min Act: -0.0001

Data Index: 657327 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1440322 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4776. Min Act: -0.0001

Data Index: 1573590 (Python Code)

Max Activating Token Index: 332

Text #17

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4605. Min Act: -0.0001

Data Index: 833092 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4650. Min Act: -0.0001

Data Index: 793912 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4618. Min Act: -0.0001

Data Index: 1518258 (Python Code)

Max Activating Token Index: 620