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

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

Neuron 3698 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.4901. Min Act: -0.0000

Data Index: 821488 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.4232. Min Act: -0.0000

Data Index: 43329 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3992. Min Act: -0.0000

Data Index: 495573 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1048724 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3773. Min Act: -0.0000

Data Index: 958273 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.4048. Min Act: -0.0000

Data Index: 897746 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3825. Min Act: -0.0000

Data Index: 725972 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3775. Min Act: -0.0000

Data Index: 485098 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3922. Min Act: -0.0000

Data Index: 861356 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1019506 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3687. Min Act: -0.0000

Data Index: 614018 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3935. Min Act: -0.0000

Data Index: 168002 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3566. Min Act: -0.0000

Data Index: 486690 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3986. Min Act: -0.0000

Data Index: 32244 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3883. Min Act: -0.0000

Data Index: 750243 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1149125 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3687. Min Act: -0.0000

Data Index: 5101 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1293557 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3761. Min Act: -0.0000

Data Index: 134 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3538. Min Act: -0.0000

Data Index: 742973 (C4 (Web Text))

Max Activating Token Index: 206