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

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

Neuron 4122 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: 5.4823. Min Range: -5.4823

Max Act: 5.4498. Min Act: -0.0000

Data Index: 1174524 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.4823. Min Act: -0.0000

Data Index: 1097744 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.2725. Min Act: -0.0000

Data Index: 40476 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.4562. Min Act: -0.0000

Data Index: 449019 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.3979. Min Act: -0.0000

Data Index: 184552 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.2865. Min Act: -0.0000

Data Index: 216109 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.2711. Min Act: -0.0000

Data Index: 1116044 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.1456. Min Act: -0.0000

Data Index: 268042 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.1242. Min Act: -0.0000

Data Index: 207916 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.0931. Min Act: -0.0000

Data Index: 226825 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.2701. Min Act: -0.0000

Data Index: 209360 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 5.4823. Min Range: -5.4823

Max Act: 4.8744. Min Act: -0.0000

Data Index: 163522 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.0275. Min Act: -0.0000

Data Index: 14269 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.0211. Min Act: -0.0000

Data Index: 1117134 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 5.4823. Min Range: -5.4823

Max Act: 4.8120. Min Act: -0.0000

Data Index: 925266 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.2221. Min Act: -0.0000

Data Index: 118328 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 5.4823. Min Range: -5.4823

Max Act: 4.8718. Min Act: -0.0000

Data Index: 1308776 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 5.4823. Min Range: -5.4823

Max Act: 5.0319. Min Act: -0.0000

Data Index: 752693 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 5.4823. Min Range: -5.4823

Max Act: 4.8488. Min Act: -0.0000

Data Index: 954152 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 5.4823. Min Range: -5.4823

Max Act: 4.5834. Min Act: -0.0000

Data Index: 1313100 (C4 (Web Text))

Max Activating Token Index: 144