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

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

Neuron 2517 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9923. Min Act: -0.0000

Data Index: 240808 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1119733 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.0003. Min Range: -1.0003

Max Act: 1.0003. Min Act: -0.0000

Data Index: 709690 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8817. Min Act: -0.0000

Data Index: 381651 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9301. Min Act: -0.0000

Data Index: 872593 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9455. Min Act: -0.0000

Data Index: 238377 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1163819 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8788. Min Act: -0.0000

Data Index: 491926 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1079293 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1207755 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8218. Min Act: -0.0000

Data Index: 382435 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1318486 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8685. Min Act: -0.0000

Data Index: 696048 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9370. Min Act: -0.0000

Data Index: 463039 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8137. Min Act: -0.0000

Data Index: 304152 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8410. Min Act: -0.0000

Data Index: 290909 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1282257 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9088. Min Act: -0.0000

Data Index: 198025 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8127. Min Act: -0.0000

Data Index: 393472 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8347. Min Act: -0.0000

Data Index: 807251 (C4 (Web Text))

Max Activating Token Index: 1002