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

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

Neuron 1367 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.8196. Min Act: -0.0001

Data Index: 968358 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.6860. Min Act: -0.0001

Data Index: 740567 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.6256. Min Act: -0.0001

Data Index: 1273431 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.5494. Min Act: -0.0001

Data Index: 1166598 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.5336. Min Act: -0.0001

Data Index: 58971 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1343338 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.5076. Min Act: -0.0001

Data Index: 1273126 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4669. Min Act: -0.0001

Data Index: 1208969 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4596. Min Act: -0.0001

Data Index: 969213 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4755. Min Act: -0.0001

Data Index: 41294 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4317. Min Act: -0.0001

Data Index: 190728 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4393. Min Act: -0.0001

Data Index: 428716 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4554. Min Act: -0.0001

Data Index: 624154 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4682. Min Act: -0.0001

Data Index: 1102653 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1330890 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4495. Min Act: -0.0001

Data Index: 773850 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4345. Min Act: -0.0001

Data Index: 672460 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4463. Min Act: -0.0001

Data Index: 504748 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4121. Min Act: -0.0001

Data Index: 956601 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.8196. Min Range: -0.8196

Max Act: 0.4212. Min Act: -0.0001

Data Index: 1231863 (C4 (Web Text))

Max Activating Token Index: 104