Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4160 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3700. Min Range: -1.3700

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1506894 (Python Code)

Max Activating Token Index: 97

Text #1

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1554917 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1640768 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1439648 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1459539 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4783. Min Act: -0.0000

Data Index: 566575 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1169804 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1452198 (Python Code)

Max Activating Token Index: 423

Text #8

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1422599 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4440. Min Act: -0.0000

Data Index: 356709 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1244976 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.3825. Min Act: -0.0000

Data Index: 492620 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.3955. Min Act: -0.0000

Data Index: 655985 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4039. Min Act: -0.0000

Data Index: 552424 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1582515 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.3863. Min Act: -0.0000

Data Index: 814043 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.3933. Min Act: -0.0000

Data Index: 374308 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.3797. Min Act: -0.0000

Data Index: 759463 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.4056. Min Act: -0.0000

Data Index: 157867 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 1.3700. Min Range: -1.3700

Max Act: 0.3822. Min Act: 0.0000

Data Index: 1369284 (Python Code)

Max Activating Token Index: 607