Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2379 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6512. Min Act: -0.0000

Data Index: 151801 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1159743 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1060047 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1062114 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6303. Min Act: -0.0000

Data Index: 79421 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1194416 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5872. Min Act: -0.0000

Data Index: 55323 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1256470 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6537. Min Act: -0.0000

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6095. Min Act: -0.0000

Data Index: 939557 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6336. Min Act: -0.0000

Data Index: 201736 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6019. Min Act: -0.0000

Data Index: 704975 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6469. Min Act: -0.0000

Data Index: 725111 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6115. Min Act: -0.0000

Data Index: 874183 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5909. Min Act: -0.0000

Data Index: 753498 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1064440 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5730. Min Act: -0.0000

Data Index: 600471 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1219053 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.6150. Min Act: -0.0000

Data Index: 160725 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.6920. Min Range: -0.6920

Max Act: 0.5596. Min Act: -0.0000

Data Index: 142897 (C4 (Web Text))

Max Activating Token Index: 589