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

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

Neuron 5083 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: 2.1043. Min Range: -2.1043

Max Act: 2.1043. Min Act: -0.0000

Data Index: 961800 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.8513. Min Act: -0.0000

Data Index: 1167022 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1141211 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.7955. Min Act: -0.0000

Data Index: 1048742 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.7791. Min Act: -0.0000

Data Index: 808386 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.6667. Min Act: -0.0000

Data Index: 992838 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.8039. Min Act: -0.0000

Data Index: 107196 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.6169. Min Act: -0.0000

Data Index: 42169 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.6456. Min Act: -0.0000

Data Index: 913422 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.4051. Min Act: -0.0000

Data Index: 317707 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.6463. Min Act: -0.0000

Data Index: 45251 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.5483. Min Act: -0.0000

Data Index: 1192094 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.5648. Min Act: -0.0000

Data Index: 24589 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.3865. Min Act: -0.0000

Data Index: 224031 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.4788. Min Act: -0.0000

Data Index: 545553 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.3824. Min Act: -0.0000

Data Index: 1303692 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.3627. Min Act: -0.0000

Data Index: 660510 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1289843 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.4223. Min Act: -0.0000

Data Index: 226700 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 2.1043. Min Range: -2.1043

Max Act: 1.3402. Min Act: -0.0000

Data Index: 209667 (C4 (Web Text))

Max Activating Token Index: 617