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

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

Neuron 1984 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: 1.9064. Min Range: -1.9064

Max Act: 1.9064. Min Act: -0.0002

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.8974. Min Act: -0.0002

Data Index: 834403 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.8662. Min Act: -0.0002

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.8623. Min Act: -0.0002

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.8149. Min Act: -0.0002

Data Index: 1122409 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.8431. Min Act: -0.0002

Data Index: 1338042 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.8019. Min Act: -0.0002

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.7524. Min Act: -0.0002

Data Index: 722737 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.7598. Min Act: -0.0002

Data Index: 240350 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.6796. Min Act: -0.0002

Data Index: 295103 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.6769. Min Act: -0.0002

Data Index: 923496 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.6903. Min Act: -0.0002

Data Index: 502125 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.6948. Min Act: -0.0002

Data Index: 1291743 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.6146. Min Act: -0.0003

Data Index: 768772 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.6143. Min Act: -0.0002

Data Index: 693961 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.5941. Min Act: -0.0002

Data Index: 483192 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.5962. Min Act: -0.0001

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.5933. Min Act: -0.0002

Data Index: 274104 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.5724. Min Act: -0.0002

Data Index: 859454 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.9064. Min Range: -1.9064

Max Act: 1.5497. Min Act: -0.0002

Data Index: 93647 (C4 (Web Text))

Max Activating Token Index: 297