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

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

Neuron 4760 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0548. Min Range: -2.0548

Max Act: 2.0548. Min Act: -0.0000

Data Index: 783847 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.8306. Min Act: -0.0000

Data Index: 614191 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1275696 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.7045. Min Act: -0.0000

Data Index: 382305 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.6819. Min Act: -0.0000

Data Index: 962579 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.7621. Min Act: -0.0000

Data Index: 426882 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.6396. Min Act: -0.0000

Data Index: 1206717 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.6423. Min Act: -0.0000

Data Index: 588847 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.6177. Min Act: -0.0000

Data Index: 166245 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.6022. Min Act: -0.0000

Data Index: 632162 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.6993. Min Act: -0.0000

Data Index: 849056 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.5113. Min Act: -0.0000

Data Index: 605885 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.5836. Min Act: -0.0000

Data Index: 1156365 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.5013. Min Act: -0.0000

Data Index: 262711 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1092524 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.5493. Min Act: -0.0000

Data Index: 913512 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.5171. Min Act: -0.0000

Data Index: 459513 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.5161. Min Act: -0.0000

Data Index: 46692 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1340964 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 2.0548. Min Range: -2.0548

Max Act: 1.4982. Min Act: -0.0000

Data Index: 626653 (C4 (Web Text))

Max Activating Token Index: 23