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

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

Neuron 4068 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2990. Min Range: -2.2990

Max Act: 2.1985. Min Act: -0.0000

Data Index: 408193 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 2.2990. Min Range: -2.2990

Max Act: 2.2990. Min Act: -0.0000

Data Index: 1065906 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.8281. Min Act: -0.0000

Data Index: 356148 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.6907. Min Act: -0.0000

Data Index: 247456 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.6452. Min Act: -0.0000

Data Index: 547320 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.6999. Min Act: -0.0001

Data Index: 655068 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.3614. Min Act: -0.0000

Data Index: 393392 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.4893. Min Act: -0.0000

Data Index: 538818 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.4782. Min Act: -0.0000

Data Index: 994991 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.4278. Min Act: -0.0000

Data Index: 649907 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.3240. Min Act: -0.0000

Data Index: 850357 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.2547. Min Act: -0.0001

Data Index: 216121 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.3984. Min Act: -0.0000

Data Index: 748558 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.3667. Min Act: -0.0000

Data Index: 263408 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.4032. Min Act: -0.0000

Data Index: 667783 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.2961. Min Act: -0.0000

Data Index: 343805 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.3105. Min Act: -0.0000

Data Index: 639981 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.2653. Min Act: -0.0000

Data Index: 536322 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.3062. Min Act: -0.0000

Data Index: 947291 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.2990. Min Range: -2.2990

Max Act: 1.3527. Min Act: -0.0001

Data Index: 764452 (C4 (Web Text))

Max Activating Token Index: 474