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

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

Neuron 2700 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.9685. Min Act: -0.0000

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.8628. Min Act: 0.0004

Data Index: 303472 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.7726. Min Act: 0.0004

Data Index: 836602 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.7925. Min Act: -0.0000

Data Index: 790632 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.7256. Min Act: -0.0000

Data Index: 755518 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.7205. Min Act: 0.0000

Data Index: 697896 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6946. Min Act: 0.0003

Data Index: 1596543 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.7154. Min Act: 0.0001

Data Index: 1399279 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6498. Min Act: 0.0001

Data Index: 1309684 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1122186 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1239980 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6610. Min Act: -0.0000

Data Index: 185576 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6381. Min Act: 0.0001

Data Index: 1439839 (Python Code)

Max Activating Token Index: 523

Text #13

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6320. Min Act: -0.0000

Data Index: 737154 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6714. Min Act: 0.0004

Data Index: 437193 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6443. Min Act: -0.0000

Data Index: 771171 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6176. Min Act: 0.0001

Data Index: 597711 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6335. Min Act: 0.0004

Data Index: 771875 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.5875. Min Act: 0.0003

Data Index: 1474716 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 0.9685. Min Range: -0.9685

Max Act: 0.6358. Min Act: 0.0003

Data Index: 1501430 (Python Code)

Max Activating Token Index: 141