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

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

Neuron 4486 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.0250. Min Range: -2.0250

Max Act: 2.0250. Min Act: -0.0002

Data Index: 709020 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8544. Min Act: -0.0002

Data Index: 272188 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8278. Min Act: -0.0002

Data Index: 916306 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8116. Min Act: -0.0002

Data Index: 919317 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7654. Min Act: -0.0002

Data Index: 1168892 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7626. Min Act: -0.0003

Data Index: 1170799 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7229. Min Act: -0.0002

Data Index: 269145 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7301. Min Act: -0.0002

Data Index: 794221 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7039. Min Act: -0.0002

Data Index: 770978 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7481. Min Act: -0.0002

Data Index: 1169755 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7845. Min Act: -0.0002

Data Index: 293054 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6980. Min Act: -0.0002

Data Index: 712395 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7433. Min Act: -0.0003

Data Index: 1093486 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7045. Min Act: -0.0002

Data Index: 907429 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6965. Min Act: -0.0002

Data Index: 201436 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7239. Min Act: -0.0002

Data Index: 1316076 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7050. Min Act: -0.0002

Data Index: 299676 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7011. Min Act: -0.0002

Data Index: 585998 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6836. Min Act: -0.0002

Data Index: 542487 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6686. Min Act: -0.0002

Data Index: 271734 (C4 (Web Text))

Max Activating Token Index: 2