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

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

Neuron 2188 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.5280. Min Act: -0.0000

Data Index: 693976 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1522396 (Python Code)

Max Activating Token Index: 981

Text #2

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1635867 (Python Code)

Max Activating Token Index: 487

Text #3

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1476466 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1393952 (Python Code)

Max Activating Token Index: 646

Text #5

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1515935 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4731. Min Act: -0.0000

Data Index: 672310 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1536046 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4579. Min Act: -0.0000

Data Index: 558118 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1638966 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4541. Min Act: -0.0000

Data Index: 42905 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1469716 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1591673 (Python Code)

Max Activating Token Index: 611

Text #13

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1423256 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1531335 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1408923 (Python Code)

Max Activating Token Index: 400

Text #16

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1541964 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1538523 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1381738 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1609259 (Python Code)

Max Activating Token Index: 213