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

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

Neuron 39 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.3040. Min Act: -0.0001

Data Index: 67879 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.3488. Min Act: -0.0002

Data Index: 338541 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.3017. Min Act: -0.0002

Data Index: 285528 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.2237. Min Act: -0.0001

Data Index: 998741 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.2061. Min Act: -0.0001

Data Index: 481205 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.2369. Min Act: -0.0001

Data Index: 42046 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.1371. Min Act: -0.0001

Data Index: 662109 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.1333. Min Act: -0.0001

Data Index: 946811 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9769. Min Act: -0.0002

Data Index: 475793 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0929. Min Act: -0.0002

Data Index: 1254093 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0518. Min Act: -0.0002

Data Index: 668172 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0974. Min Act: -0.0002

Data Index: 1207544 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9909. Min Act: -0.0001

Data Index: 1134652 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0328. Min Act: -0.0002

Data Index: 268708 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0367. Min Act: -0.0001

Data Index: 856426 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.8239. Min Act: -0.0002

Data Index: 105970 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0752. Min Act: -0.0001

Data Index: 998346 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0932. Min Act: -0.0001

Data Index: 332319 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.1133. Min Act: -0.0001

Data Index: 374356 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9992. Min Act: -0.0001

Data Index: 635225 (C4 (Web Text))

Max Activating Token Index: 342