Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 833 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0561. Min Range: -2.0561

Max Act: 2.0561. Min Act: -0.0000

Data Index: 146712 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.7697. Min Act: -0.0000

Data Index: 268095 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.6963. Min Act: -0.0001

Data Index: 1332339 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.6275. Min Act: -0.0001

Data Index: 935963 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.6041. Min Act: -0.0001

Data Index: 430109 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.5639. Min Act: -0.0000

Data Index: 1119330 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.5047. Min Act: -0.0000

Data Index: 746946 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.5061. Min Act: -0.0000

Data Index: 955802 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1039210 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1068563 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.4138. Min Act: -0.0000

Data Index: 755405 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1088328 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.4084. Min Act: -0.0000

Data Index: 350846 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.3685. Min Act: -0.0001

Data Index: 1104734 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.4039. Min Act: -0.0000

Data Index: 131667 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1334720 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.4196. Min Act: -0.0001

Data Index: 40370 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.3729. Min Act: -0.0000

Data Index: 838025 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.3692. Min Act: -0.0000

Data Index: 663926 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 2.0561. Min Range: -2.0561

Max Act: 1.4038. Min Act: -0.0000

Data Index: 108950 (C4 (Web Text))

Max Activating Token Index: 616