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

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

Neuron 6067 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: 1.6742. Min Range: -1.6742

Max Act: 1.6742. Min Act: -0.0002

Data Index: 143119 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.4648. Min Act: -0.0002

Data Index: 1186998 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.3724. Min Act: -0.0002

Data Index: 87641 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2814. Min Act: -0.0002

Data Index: 561175 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.3342. Min Act: -0.0002

Data Index: 397481 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.3234. Min Act: -0.0002

Data Index: 1023694 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2834. Min Act: -0.0002

Data Index: 1163094 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.3118. Min Act: -0.0002

Data Index: 473051 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2482. Min Act: -0.0002

Data Index: 974587 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2036. Min Act: -0.0003

Data Index: 1243216 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2758. Min Act: -0.0002

Data Index: 1181225 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.1957. Min Act: -0.0002

Data Index: 661277 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2304. Min Act: -0.0002

Data Index: 683211 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2360. Min Act: -0.0002

Data Index: 166518 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2353. Min Act: -0.0002

Data Index: 546925 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2085. Min Act: -0.0003

Data Index: 1202892 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2324. Min Act: -0.0002

Data Index: 374574 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.2091. Min Act: -0.0002

Data Index: 231817 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.1496. Min Act: -0.0002

Data Index: 547799 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.6742. Min Range: -1.6742

Max Act: 1.1614. Min Act: -0.0002

Data Index: 736860 (C4 (Web Text))

Max Activating Token Index: 545