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

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

Neuron 3349 in Layer 0

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: 1.0453. Min Range: -1.0453

Max Act: 1.0367. Min Act: -0.0001

Data Index: 196580 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0453. Min Act: -0.0001

Data Index: 1319059 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0330. Min Act: -0.0001

Data Index: 976167 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0241. Min Act: -0.0001

Data Index: 785615 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0094. Min Act: -0.0002

Data Index: 983425 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9774. Min Act: -0.0001

Data Index: 236698 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9882. Min Act: -0.0001

Data Index: 1326452 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9704. Min Act: -0.0001

Data Index: 543298 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9798. Min Act: -0.0001

Data Index: 105605 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9688. Min Act: -0.0001

Data Index: 188955 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9623. Min Act: -0.0001

Data Index: 707306 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9687. Min Act: -0.0001

Data Index: 240667 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9550. Min Act: -0.0001

Data Index: 1150654 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9572. Min Act: -0.0002

Data Index: 156688 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9691. Min Act: -0.0001

Data Index: 200336 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9557. Min Act: -0.0001

Data Index: 429586 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9646. Min Act: -0.0001

Data Index: 1048159 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9533. Min Act: -0.0001

Data Index: 1353710 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9605. Min Act: -0.0001

Data Index: 370247 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.9638. Min Act: -0.0001

Data Index: 144705 (C4 (Web Text))

Max Activating Token Index: 426