Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 117 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.7274. Min Act: -0.0000

Data Index: 306031 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.8287. Min Act: -0.0000

Data Index: 1271117 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1602511 (Python Code)

Max Activating Token Index: 293

Text #3

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.6702. Min Act: -0.0000

Data Index: 1162749 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5803. Min Act: -0.0000

Data Index: 656949 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.6208. Min Act: -0.0000

Data Index: 1459968 (Python Code)

Max Activating Token Index: 392

Text #6

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5045. Min Act: -0.0000

Data Index: 999757 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.2371. Min Act: -0.0001

Data Index: 1583913 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5816. Min Act: -0.0000

Data Index: 693049 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3698. Min Act: -0.0000

Data Index: 639054 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1538730 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1626485 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4708. Min Act: -0.0000

Data Index: 1583790 (Python Code)

Max Activating Token Index: 489

Text #13

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1383442 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4529. Min Act: -0.0000

Data Index: 1648376 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4439. Min Act: -0.0000

Data Index: 1435 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4375. Min Act: -0.0000

Data Index: 713398 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3923. Min Act: -0.0000

Data Index: 530303 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1528120 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1306131 (C4 (Web Text))

Max Activating Token Index: 164