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

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

Neuron 1387 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1251167 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6541. Min Act: -0.0000

Data Index: 492626 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6460. Min Act: -0.0000

Data Index: 371700 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1148108 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5489. Min Act: -0.0000

Data Index: 527209 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1033025 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1127639 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5731. Min Act: -0.0000

Data Index: 106665 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5476. Min Act: -0.0000

Data Index: 910866 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5200. Min Act: -0.0000

Data Index: 539238 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5206. Min Act: -0.0000

Data Index: 963736 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1215158 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4805. Min Act: -0.0000

Data Index: 940981 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4720. Min Act: -0.0000

Data Index: 731367 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4848. Min Act: -0.0000

Data Index: 106719 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4869. Min Act: -0.0000

Data Index: 958296 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4646. Min Act: -0.0000

Data Index: 996379 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4673. Min Act: -0.0000

Data Index: 862601 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4860. Min Act: -0.0000

Data Index: 903003 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4608. Min Act: -0.0000

Data Index: 512883 (C4 (Web Text))

Max Activating Token Index: 161