Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 264 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.6019. Min Act: -0.0001

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5939. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5261. Min Act: -0.0001

Data Index: 633416 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5219. Min Act: -0.0001

Data Index: 214674 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5039. Min Act: -0.0001

Data Index: 906983 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4309. Min Act: -0.0001

Data Index: 168622 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4329. Min Act: -0.0001

Data Index: 229515 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4143. Min Act: -0.0001

Data Index: 716044 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3819. Min Act: -0.0001

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3743. Min Act: -0.0001

Data Index: 485983 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3651. Min Act: -0.0001

Data Index: 748935 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3580. Min Act: -0.0001

Data Index: 444431 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3427. Min Act: -0.0001

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3643. Min Act: -0.0001

Data Index: 272982 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1029781 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3490. Min Act: -0.0001

Data Index: 989106 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3444. Min Act: -0.0001

Data Index: 1025273 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3525. Min Act: -0.0001

Data Index: 1138907 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3478. Min Act: -0.0001

Data Index: 994661 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3416. Min Act: -0.0001

Data Index: 751644 (C4 (Web Text))

Max Activating Token Index: 191