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

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

Neuron 753 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.8729. Min Act: -0.0000

Data Index: 728768 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7729. Min Act: -0.0001

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7249. Min Act: -0.0001

Data Index: 1641936 (Python Code)

Max Activating Token Index: 570

Text #3

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7104. Min Act: -0.0001

Data Index: 1426567 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6231. Min Act: -0.0001

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6522. Min Act: -0.0000

Data Index: 543888 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7024. Min Act: -0.0000

Data Index: 589030 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6358. Min Act: -0.0000

Data Index: 142595 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1183449 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6215. Min Act: -0.0000

Data Index: 34391 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6363. Min Act: -0.0001

Data Index: 500029 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1129930 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1198776 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6358. Min Act: -0.0000

Data Index: 652414 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5983. Min Act: -0.0000

Data Index: 642358 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1124842 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6054. Min Act: -0.0000

Data Index: 753521 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5930. Min Act: -0.0000

Data Index: 179661 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5577. Min Act: -0.0000

Data Index: 204837 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6059. Min Act: -0.0000

Data Index: 961135 (C4 (Web Text))

Max Activating Token Index: 520