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

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

Neuron 2424 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7975. Min Act: -0.0001

Data Index: 947978 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7504. Min Act: -0.0001

Data Index: 32456 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1037603 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7018. Min Act: -0.0001

Data Index: 756880 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1097579 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6220. Min Act: -0.0000

Data Index: 664384 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5664. Min Act: -0.0001

Data Index: 1051819 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6320. Min Act: -0.0000

Data Index: 685158 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5399. Min Act: -0.0000

Data Index: 84261 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5740. Min Act: -0.0000

Data Index: 724181 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5290. Min Act: -0.0001

Data Index: 1108488 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5149. Min Act: -0.0001

Data Index: 913377 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5030. Min Act: -0.0001

Data Index: 15427 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5059. Min Act: -0.0000

Data Index: 520845 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.4775. Min Act: -0.0001

Data Index: 766719 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.4781. Min Act: -0.0001

Data Index: 1016542 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.4649. Min Act: -0.0000

Data Index: 206383 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1079819 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.4589. Min Act: -0.0001

Data Index: 538208 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.4685. Min Act: -0.0001

Data Index: 590785 (C4 (Web Text))

Max Activating Token Index: 902