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

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

Neuron 5813 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: 2.3458. Min Range: -2.3458

Max Act: 2.3291. Min Act: -0.0001

Data Index: 213689 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.3458. Min Act: -0.0001

Data Index: 728220 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.2103. Min Act: -0.0001

Data Index: 587847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.1733. Min Act: -0.0001

Data Index: 905582 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.1377. Min Act: -0.0001

Data Index: 1036432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.0951. Min Act: -0.0001

Data Index: 1337352 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.0104. Min Act: -0.0001

Data Index: 900573 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.0227. Min Act: -0.0001

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 2.3458. Min Range: -2.3458

Max Act: 2.0441. Min Act: -0.0001

Data Index: 1267968 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9945. Min Act: -0.0001

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9880. Min Act: -0.0001

Data Index: 318012 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9500. Min Act: -0.0001

Data Index: 713385 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9468. Min Act: -0.0001

Data Index: 495360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9421. Min Act: -0.0001

Data Index: 709014 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9281. Min Act: -0.0001

Data Index: 188196 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9166. Min Act: -0.0001

Data Index: 1127948 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9369. Min Act: -0.0001

Data Index: 47834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9554. Min Act: -0.0001

Data Index: 1132707 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9513. Min Act: -0.0001

Data Index: 126002 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 2.3458. Min Range: -2.3458

Max Act: 1.9058. Min Act: -0.0001

Data Index: 359546 (C4 (Web Text))

Max Activating Token Index: 1023