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

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

Neuron 3800 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3046. Min Range: -2.3046

Max Act: 2.3046. Min Act: -0.0000

Data Index: 276753 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 2.3046. Min Range: -2.3046

Max Act: 2.0399. Min Act: -0.0000

Data Index: 1230599 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.6896. Min Act: -0.0000

Data Index: 387115 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.7143. Min Act: -0.0000

Data Index: 562453 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.9257. Min Act: -0.0000

Data Index: 638806 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.6066. Min Act: -0.0000

Data Index: 1028592 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.7986. Min Act: -0.0000

Data Index: 571833 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.7945. Min Act: -0.0000

Data Index: 977896 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.8077. Min Act: -0.0000

Data Index: 725952 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.5716. Min Act: -0.0000

Data Index: 128868 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.5730. Min Act: -0.0000

Data Index: 1262020 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1270410 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.5176. Min Act: -0.0000

Data Index: 1119648 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.5049. Min Act: -0.0000

Data Index: 189234 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.4624. Min Act: -0.0000

Data Index: 844697 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.4278. Min Act: -0.0000

Data Index: 425799 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1306624 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.3328. Min Act: -0.0000

Data Index: 100227 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.3763. Min Act: 0.0000

Data Index: 469870 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 2.3046. Min Range: -2.3046

Max Act: 1.3835. Min Act: -0.0000

Data Index: 711265 (C4 (Web Text))

Max Activating Token Index: 1020