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

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

Neuron 788 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1342065 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.4958. Min Act: -0.0001

Data Index: 57416 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.3419. Min Act: -0.0001

Data Index: 2153 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.3124. Min Act: -0.0001

Data Index: 400466 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1042284 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.3269. Min Act: -0.0001

Data Index: 817482 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.3230. Min Act: -0.0001

Data Index: 684545 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2943. Min Act: -0.0001

Data Index: 626449 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2924. Min Act: -0.0001

Data Index: 809422 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2835. Min Act: -0.0001

Data Index: 572495 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2912. Min Act: -0.0001

Data Index: 239119 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2783. Min Act: -0.0001

Data Index: 506664 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2696. Min Act: -0.0001

Data Index: 178932 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1333685 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2972. Min Act: -0.0001

Data Index: 245633 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2875. Min Act: -0.0001

Data Index: 1357929 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1228287 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2762. Min Act: -0.0001

Data Index: 803414 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.3052. Min Act: -0.0001

Data Index: 617604 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.5276. Min Range: -0.5276

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1120480 (C4 (Web Text))

Max Activating Token Index: 315