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

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

Neuron 6053 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.8587. Min Act: -0.0000

Data Index: 905141 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.4374. Min Act: -0.0000

Data Index: 362615 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.4419. Min Act: -0.0000

Data Index: 709676 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.3726. Min Act: -0.0000

Data Index: 1323847 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.1508. Min Act: -0.0000

Data Index: 179941 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.2879. Min Act: -0.0000

Data Index: 235078 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.2747. Min Act: -0.0000

Data Index: 803189 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.2133. Min Act: -0.0000

Data Index: 1333430 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.2077. Min Act: -0.0000

Data Index: 1325681 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.1536. Min Act: -0.0000

Data Index: 79905 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.1494. Min Act: -0.0000

Data Index: 1074264 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.8352. Min Act: -0.0000

Data Index: 489627 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.9906. Min Act: -0.0000

Data Index: 974017 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 6.8587. Min Range: -6.8587

Max Act: 6.1242. Min Act: -0.0000

Data Index: 663492 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.9214. Min Act: -0.0000

Data Index: 659932 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.9080. Min Act: -0.0000

Data Index: 1253752 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.8775. Min Act: -0.0000

Data Index: 61053 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.8329. Min Act: -0.0000

Data Index: 589105 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.8195. Min Act: -0.0000

Data Index: 1050512 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 6.8587. Min Range: -6.8587

Max Act: 5.8145. Min Act: -0.0000

Data Index: 1144382 (C4 (Web Text))

Max Activating Token Index: 561