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

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

Neuron 918 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: 7.3526. Min Range: -7.3526

Max Act: 7.3526. Min Act: -0.0000

Data Index: 854200 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 7.3526. Min Range: -7.3526

Max Act: 7.2812. Min Act: -0.0000

Data Index: 167473 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 7.3526. Min Range: -7.3526

Max Act: 7.2036. Min Act: -0.0000

Data Index: 405594 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 7.3526. Min Range: -7.3526

Max Act: 6.9750. Min Act: -0.0000

Data Index: 896401 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 7.3526. Min Range: -7.3526

Max Act: 7.1587. Min Act: -0.0000

Data Index: 1125237 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 7.3526. Min Range: -7.3526

Max Act: 6.9823. Min Act: -0.0000

Data Index: 949647 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 7.3526. Min Range: -7.3526

Max Act: 6.3342. Min Act: -0.0000

Data Index: 453067 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 7.3526. Min Range: -7.3526

Max Act: 6.0454. Min Act: -0.0000

Data Index: 86094 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 7.3526. Min Range: -7.3526

Max Act: 6.3574. Min Act: -0.0000

Data Index: 1100443 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 7.3526. Min Range: -7.3526

Max Act: 6.1753. Min Act: -0.0000

Data Index: 246818 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.7386. Min Act: -0.0000

Data Index: 68376 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.7358. Min Act: -0.0000

Data Index: 768601 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.6314. Min Act: -0.0000

Data Index: 95765 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.5907. Min Act: -0.0000

Data Index: 97446 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.6450. Min Act: -0.0000

Data Index: 492534 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.4534. Min Act: -0.0000

Data Index: 394498 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.8244. Min Act: -0.0000

Data Index: 1038624 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.8277. Min Act: -0.0000

Data Index: 122639 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.8169. Min Act: -0.0000

Data Index: 445040 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 7.3526. Min Range: -7.3526

Max Act: 5.5299. Min Act: -0.0000

Data Index: 1308148 (C4 (Web Text))

Max Activating Token Index: 944