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

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

Neuron 597 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0614. Min Range: -2.0614

Max Act: 2.0614. Min Act: -0.0000

Data Index: 989646 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 2.0614. Min Range: -2.0614

Max Act: 2.0298. Min Act: -0.0000

Data Index: 996532 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.7727. Min Act: -0.0000

Data Index: 834534 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.8535. Min Act: -0.0000

Data Index: 1166077 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1272823 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6108. Min Act: -0.0000

Data Index: 85251 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5550. Min Act: -0.0000

Data Index: 1067539 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6590. Min Act: -0.0000

Data Index: 455690 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6754. Min Act: -0.0000

Data Index: 865708 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3136. Min Act: -0.0000

Data Index: 733182 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.4764. Min Act: -0.0000

Data Index: 385608 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5385. Min Act: -0.0000

Data Index: 177520 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.4487. Min Act: -0.0000

Data Index: 36803 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.4768. Min Act: -0.0000

Data Index: 268429 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3829. Min Act: -0.0000

Data Index: 466732 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5024. Min Act: -0.0000

Data Index: 1225969 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1200233 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3577. Min Act: -0.0000

Data Index: 1097399 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3659. Min Act: -0.0000

Data Index: 385709 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3947. Min Act: -0.0000

Data Index: 367755 (C4 (Web Text))

Max Activating Token Index: 573