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

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

Neuron 5422 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: 3.5796. Min Range: -3.5796

Max Act: 3.5796. Min Act: -0.0000

Data Index: 980441 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.5535. Min Act: -0.0000

Data Index: 779238 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2528. Min Act: -0.0000

Data Index: 537995 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3665. Min Act: -0.0000

Data Index: 965695 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.0909. Min Act: -0.0000

Data Index: 673383 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.0992. Min Act: -0.0000

Data Index: 1277358 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.9776. Min Act: -0.0000

Data Index: 332965 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.8950. Min Act: -0.0000

Data Index: 1206324 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.6438. Min Act: -0.0000

Data Index: 191511 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.7058. Min Act: -0.0000

Data Index: 87410 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.8544. Min Act: -0.0000

Data Index: 503006 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.5550. Min Act: -0.0000

Data Index: 553613 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.2350. Min Act: -0.0000

Data Index: 572419 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.2042. Min Act: -0.0000

Data Index: 857026 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.3100. Min Act: -0.0000

Data Index: 40998 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.2828. Min Act: -0.0000

Data Index: 259978 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.1743. Min Act: -0.0000

Data Index: 702035 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.3380. Min Act: -0.0000

Data Index: 816053 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.0130. Min Act: -0.0000

Data Index: 1064599 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 3.5796. Min Range: -3.5796

Max Act: 2.0889. Min Act: -0.0000

Data Index: 1057925 (C4 (Web Text))

Max Activating Token Index: 418