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

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

Neuron 783 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: 1.9007. Min Range: -1.9007

Max Act: 1.8933. Min Act: -0.0002

Data Index: 551728 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.9007. Min Act: -0.0002

Data Index: 247606 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.6706. Min Act: -0.0002

Data Index: 417979 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.6673. Min Act: -0.0002

Data Index: 1296344 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.6264. Min Act: -0.0002

Data Index: 1468612 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.6136. Min Act: -0.0002

Data Index: 1574562 (Python Code)

Max Activating Token Index: 757

Text #6

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5774. Min Act: -0.0002

Data Index: 1569307 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.6135. Min Act: -0.0002

Data Index: 586875 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5276. Min Act: -0.0002

Data Index: 1494412 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5842. Min Act: -0.0002

Data Index: 1614692 (Python Code)

Max Activating Token Index: 205

Text #10

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5405. Min Act: -0.0002

Data Index: 1522265 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5122. Min Act: -0.0002

Data Index: 939515 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5239. Min Act: -0.0002

Data Index: 1399208 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5879. Min Act: -0.0002

Data Index: 840641 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5002. Min Act: -0.0002

Data Index: 292448 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5664. Min Act: -0.0002

Data Index: 1479288 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5357. Min Act: -0.0002

Data Index: 1544081 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5345. Min Act: -0.0002

Data Index: 583152 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.4939. Min Act: -0.0002

Data Index: 772451 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.9007. Min Range: -1.9007

Max Act: 1.5133. Min Act: -0.0002

Data Index: 653456 (C4 (Web Text))

Max Activating Token Index: 790