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

Dataset: The Pile

Neuron 2233 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.2234. Min Act: -0.0000

Data Index: 320427 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.1477. Min Act: 0.0000

Data Index: 1858160 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 1.2234. Min Range: -1.2234

Max Act: 1.0250. Min Act: -0.0000

Data Index: 481119 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9397. Min Act: 0.0001

Data Index: 953147 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9548. Min Act: 0.0000

Data Index: 305147 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8668. Min Act: -0.0000

Data Index: 87762 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9093. Min Act: -0.0000

Data Index: 526506 (The Pile)

Max Activating Token Index: 542

Text #7

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1530630 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8969. Min Act: -0.0000

Data Index: 684948 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8831. Min Act: 0.0000

Data Index: 903168 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8775. Min Act: -0.0000

Data Index: 996898 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1159365 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8739. Min Act: -0.0000

Data Index: 754875 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8424. Min Act: -0.0000

Data Index: 308121 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8462. Min Act: -0.0000

Data Index: 930170 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1760819 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8333. Min Act: 0.0000

Data Index: 1732750 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1972682 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8789. Min Act: -0.0000

Data Index: 163106 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 1.2234. Min Range: -1.2234

Max Act: 0.8243. Min Act: -0.0000

Data Index: 163112 (The Pile)

Max Activating Token Index: 865