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

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

Neuron 4714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4996. Min Act: -0.0000

Data Index: 943271 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3946. Min Act: -0.0000

Data Index: 557314 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1121465 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2854. Min Act: -0.0000

Data Index: 183147 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3016. Min Act: -0.0000

Data Index: 994470 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1150948 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2412. Min Act: -0.0000

Data Index: 267106 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1084077 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2533. Min Act: -0.0000

Data Index: 15646 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2217. Min Act: -0.0000

Data Index: 803778 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2208. Min Act: -0.0000

Data Index: 192140 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1220810 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2122. Min Act: -0.0000

Data Index: 98393 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2025. Min Act: -0.0000

Data Index: 436975 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2228. Min Act: -0.0000

Data Index: 145090 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2075. Min Act: -0.0000

Data Index: 769359 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.1939. Min Act: -0.0000

Data Index: 825789 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.1780. Min Act: -0.0000

Data Index: 189149 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1088202 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.1884. Min Act: -0.0000

Data Index: 690350 (C4 (Web Text))

Max Activating Token Index: 621