Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 931 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7418. Min Act: -0.0003

Data Index: 817248 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6794. Min Act: -0.0003

Data Index: 1189224 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5401. Min Act: -0.0003

Data Index: 25631 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5286. Min Act: -0.0003

Data Index: 495573 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4855. Min Act: -0.0003

Data Index: 69371 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5404. Min Act: -0.0003

Data Index: 429999 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5219. Min Act: -0.0003

Data Index: 3909 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5171. Min Act: -0.0003

Data Index: 1285546 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4937. Min Act: -0.0003

Data Index: 568518 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5204. Min Act: -0.0003

Data Index: 678925 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4666. Min Act: -0.0003

Data Index: 539774 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5138. Min Act: -0.0003

Data Index: 380120 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5062. Min Act: -0.0003

Data Index: 14532 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4576. Min Act: -0.0003

Data Index: 1066106 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4668. Min Act: -0.0003

Data Index: 353283 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4596. Min Act: -0.0003

Data Index: 698329 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4274. Min Act: -0.0003

Data Index: 409997 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4347. Min Act: -0.0003

Data Index: 929705 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4398. Min Act: -0.0003

Data Index: 661743 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.4001. Min Act: -0.0003

Data Index: 1065996 (C4 (Web Text))

Max Activating Token Index: 721