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

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

Neuron 3465 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.1036. Min Act: -0.0000

Data Index: 32916 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.0680. Min Act: -0.0000

Data Index: 198075 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3346. Min Act: -0.0000

Data Index: 493014 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8854. Min Act: -0.0000

Data Index: 1138471 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6795. Min Act: -0.0000

Data Index: 854992 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.7854. Min Act: -0.0000

Data Index: 1059931 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6372. Min Act: -0.0000

Data Index: 187666 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4423. Min Act: -0.0000

Data Index: 782300 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.3016. Min Act: -0.0000

Data Index: 1048808 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.5153. Min Act: -0.0000

Data Index: 475973 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.3565. Min Act: -0.0000

Data Index: 372027 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4374. Min Act: -0.0000

Data Index: 35449 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4547. Min Act: -0.0000

Data Index: 1191718 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4246. Min Act: 0.0000

Data Index: 653040 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.3202. Min Act: -0.0000

Data Index: 1374308 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4064. Min Act: -0.0000

Data Index: 1030875 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.1566. Min Act: -0.0000

Data Index: 549926 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.1394. Min Act: -0.0000

Data Index: 741085 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.2127. Min Act: -0.0000

Data Index: 495180 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.4352. Min Act: -0.0000

Data Index: 1414955 (Python Code)

Max Activating Token Index: 356