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

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

Neuron 4257 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: 1.6982. Min Range: -1.6982

Max Act: 1.6982. Min Act: -0.0000

Data Index: 707121 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.6019. Min Act: -0.0000

Data Index: 484833 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5842. Min Act: -0.0000

Data Index: 368340 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.3570. Min Act: -0.0000

Data Index: 82504 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.3836. Min Act: -0.0000

Data Index: 673913 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.3663. Min Act: -0.0000

Data Index: 588218 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1595. Min Act: -0.0000

Data Index: 350556 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.2335. Min Act: -0.0000

Data Index: 313785 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1137306 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1536. Min Act: -0.0000

Data Index: 662126 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.2803. Min Act: -0.0000

Data Index: 826919 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1768. Min Act: -0.0001

Data Index: 902696 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1543. Min Act: -0.0000

Data Index: 112158 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.2277. Min Act: -0.0000

Data Index: 877983 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1622. Min Act: -0.0000

Data Index: 679241 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1190. Min Act: -0.0000

Data Index: 776998 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1846. Min Act: -0.0000

Data Index: 195683 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1508. Min Act: -0.0000

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.0685. Min Act: -0.0000

Data Index: 163902 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1214010 (C4 (Web Text))

Max Activating Token Index: 944