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

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

Neuron 5296 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.5878. Min Act: -0.0000

Data Index: 950829 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.6265. Min Act: -0.0000

Data Index: 437045 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.5455. Min Act: -0.0000

Data Index: 151211 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1250828 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.5410. Min Act: -0.0000

Data Index: 1180565 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.4033. Min Act: -0.0000

Data Index: 303771 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.4493. Min Act: -0.0000

Data Index: 503811 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.3339. Min Act: -0.0000

Data Index: 160101 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.4651. Min Act: -0.0000

Data Index: 590287 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.3986. Min Act: -0.0000

Data Index: 403738 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.3064. Min Act: -0.0000

Data Index: 73048 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.3302. Min Act: -0.0000

Data Index: 369372 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1078515 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1063240 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1213920 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.2355. Min Act: -0.0000

Data Index: 690 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.1785. Min Act: -0.0001

Data Index: 670291 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.1977. Min Act: -0.0001

Data Index: 9514 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.2452. Min Act: -0.0001

Data Index: 529093 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.2239. Min Act: -0.0000

Data Index: 884713 (C4 (Web Text))

Max Activating Token Index: 481