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

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

Neuron 4455 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1656. Min Range: -1.1656

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1354741 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.1656. Min Range: -1.1656

Max Act: 1.1226. Min Act: -0.0000

Data Index: 782401 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.1656. Min Range: -1.1656

Max Act: 1.1182. Min Act: -0.0000

Data Index: 373450 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.1656. Min Range: -1.1656

Max Act: 1.0308. Min Act: -0.0000

Data Index: 951043 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1492705 (Python Code)

Max Activating Token Index: 551

Text #5

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9816. Min Act: -0.0000

Data Index: 321659 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9852. Min Act: -0.0000

Data Index: 856919 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9510. Min Act: -0.0000

Data Index: 808833 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.1656. Min Range: -1.1656

Max Act: 1.0244. Min Act: -0.0000

Data Index: 804090 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9509. Min Act: -0.0000

Data Index: 232914 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.8963. Min Act: -0.0000

Data Index: 25977 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9399. Min Act: -0.0000

Data Index: 679299 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9424. Min Act: -0.0000

Data Index: 925008 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9106. Min Act: -0.0000

Data Index: 721303 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9258. Min Act: -0.0000

Data Index: 44097 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.8947. Min Act: -0.0000

Data Index: 226284 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1302418 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1329736 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.8762. Min Act: -0.0000

Data Index: 507778 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.1656. Min Range: -1.1656

Max Act: 0.9342. Min Act: -0.0000

Data Index: 586575 (C4 (Web Text))

Max Activating Token Index: 219