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

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

Neuron 1029 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.6875. Min Act: -0.0000

Data Index: 1607816 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.2049. Min Act: -0.0000

Data Index: 1381616 (Python Code)

Max Activating Token Index: 295

Text #2

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.8905. Min Act: -0.0000

Data Index: 1504649 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.8332. Min Act: -0.0000

Data Index: 1612777 (Python Code)

Max Activating Token Index: 479

Text #4

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.7370. Min Act: -0.0000

Data Index: 1394135 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.1157. Min Act: -0.0000

Data Index: 1629563 (Python Code)

Max Activating Token Index: 594

Text #6

Max Range: 3.6875. Min Range: -3.6875

Max Act: 2.0628. Min Act: -0.0000

Data Index: 915961 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.8280. Min Act: -0.0000

Data Index: 1258594 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.8305. Min Act: -0.0000

Data Index: 2483 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.9230. Min Act: -0.0000

Data Index: 1043911 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.6984. Min Act: -0.0000

Data Index: 1505070 (Python Code)

Max Activating Token Index: 924

Text #11

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.9033. Min Act: -0.0000

Data Index: 262630 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.6707. Min Act: -0.0000

Data Index: 730584 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1430344 (Python Code)

Max Activating Token Index: 780

Text #14

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.6716. Min Act: -0.0000

Data Index: 61853 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.7338. Min Act: -0.0000

Data Index: 80400 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.7791. Min Act: -0.0000

Data Index: 1554334 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.6857. Min Act: -0.0000

Data Index: 1549583 (Python Code)

Max Activating Token Index: 369

Text #18

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1539560 (Python Code)

Max Activating Token Index: 834

Text #19

Max Range: 3.6875. Min Range: -3.6875

Max Act: 1.6048. Min Act: -0.0000

Data Index: 251246 (C4 (Web Text))

Max Activating Token Index: 286