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

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

Neuron 1040 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.6647. Min Act: -0.0000

Data Index: 536137 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.1301. Min Act: -0.0000

Data Index: 430552 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.1146. Min Act: -0.0000

Data Index: 1074714 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.1114. Min Act: -0.0000

Data Index: 179656 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.1206. Min Act: -0.0000

Data Index: 512377 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.9827. Min Act: -0.0000

Data Index: 557081 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.1335. Min Act: -0.0000

Data Index: 1286427 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.9448. Min Act: -0.0000

Data Index: 1293279 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.8558. Min Act: -0.0000

Data Index: 879596 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.0120. Min Act: -0.0000

Data Index: 428693 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.1195. Min Act: -0.0000

Data Index: 424369 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.7220. Min Act: -0.0000

Data Index: 683443 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.9699. Min Act: -0.0000

Data Index: 896459 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.6445. Min Act: -0.0000

Data Index: 1276576 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.6647. Min Range: -3.6647

Max Act: 3.0710. Min Act: -0.0000

Data Index: 1116381 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.9553. Min Act: -0.0000

Data Index: 434469 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.6339. Min Act: -0.0000

Data Index: 684402 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.6998. Min Act: -0.0000

Data Index: 500924 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.7464. Min Act: -0.0000

Data Index: 623407 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 3.6647. Min Range: -3.6647

Max Act: 2.8624. Min Act: -0.0000

Data Index: 875749 (C4 (Web Text))

Max Activating Token Index: 697