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

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

Neuron 3816 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7579. Min Range: -5.7579

Max Act: 5.3022. Min Act: -0.0001

Data Index: 70256 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 5.7579. Min Range: -5.7579

Max Act: 5.7579. Min Act: -0.0001

Data Index: 950772 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 5.7579. Min Range: -5.7579

Max Act: 3.9449. Min Act: -0.0001

Data Index: 1301335 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.3818. Min Act: -0.0001

Data Index: 972362 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 5.7579. Min Range: -5.7579

Max Act: 5.0483. Min Act: -0.0001

Data Index: 1325856 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.9822. Min Act: -0.0001

Data Index: 685441 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.4101. Min Act: -0.0001

Data Index: 1285104 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.5898. Min Act: -0.0001

Data Index: 222856 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 5.7579. Min Range: -5.7579

Max Act: 3.5397. Min Act: -0.0001

Data Index: 752067 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.3915. Min Act: -0.0001

Data Index: 66833 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.3083. Min Act: -0.0001

Data Index: 370104 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.5731. Min Act: -0.0001

Data Index: 1250921 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 5.7579. Min Range: -5.7579

Max Act: 5.4873. Min Act: -0.0001

Data Index: 64097 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.2042. Min Act: -0.0001

Data Index: 337212 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.3371. Min Act: -0.0001

Data Index: 341971 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.4983. Min Act: -0.0001

Data Index: 779638 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 5.7579. Min Range: -5.7579

Max Act: 3.5018. Min Act: -0.0001

Data Index: 932434 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.0822. Min Act: -0.0001

Data Index: 1031030 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 5.7579. Min Range: -5.7579

Max Act: 3.3971. Min Act: -0.0001

Data Index: 930564 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 5.7579. Min Range: -5.7579

Max Act: 4.1650. Min Act: -0.0001

Data Index: 652793 (C4 (Web Text))

Max Activating Token Index: 165