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

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

Neuron 131 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.4980. Min Act: -0.0000

Data Index: 1250114 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.1671. Min Act: -0.0000

Data Index: 651281 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.5821. Min Act: -0.0000

Data Index: 966206 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.5167. Min Act: -0.0000

Data Index: 1316750 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.3416. Min Act: -0.0000

Data Index: 1289358 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.3133. Min Act: -0.0000

Data Index: 199457 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.3828. Min Act: -0.0000

Data Index: 491248 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.2453. Min Act: -0.0000

Data Index: 695458 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.3441. Min Act: -0.0000

Data Index: 357404 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.0857. Min Act: -0.0000

Data Index: 1220315 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.1814. Min Act: -0.0000

Data Index: 1357445 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.0683. Min Act: -0.0000

Data Index: 1361378 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 3.4980. Min Range: -3.4980

Max Act: 1.8938. Min Act: -0.0000

Data Index: 971623 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.0387. Min Act: -0.0000

Data Index: 898507 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.0304. Min Act: -0.0000

Data Index: 698501 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 3.4980. Min Range: -3.4980

Max Act: 1.9357. Min Act: -0.0000

Data Index: 679504 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 3.4980. Min Range: -3.4980

Max Act: 1.9945. Min Act: -0.0000

Data Index: 816179 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 3.4980. Min Range: -3.4980

Max Act: 2.0053. Min Act: -0.0000

Data Index: 189241 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.4980. Min Range: -3.4980

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1274118 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 3.4980. Min Range: -3.4980

Max Act: 1.7473. Min Act: -0.0000

Data Index: 373127 (C4 (Web Text))

Max Activating Token Index: 777