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

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

Neuron 3456 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0094. Min Range: -1.0094

Max Act: 1.0014. Min Act: -0.0001

Data Index: 1048865 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.0094. Min Range: -1.0094

Max Act: 1.0094. Min Act: -0.0001

Data Index: 368628 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9385. Min Act: -0.0001

Data Index: 664759 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9608. Min Act: -0.0001

Data Index: 343043 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9535. Min Act: -0.0001

Data Index: 168475 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9173. Min Act: -0.0001

Data Index: 983709 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9628. Min Act: -0.0001

Data Index: 675820 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9527. Min Act: -0.0001

Data Index: 299410 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9525. Min Act: -0.0001

Data Index: 806465 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8601. Min Act: -0.0001

Data Index: 1314574 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8473. Min Act: -0.0001

Data Index: 876484 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8087. Min Act: -0.0001

Data Index: 210195 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8803. Min Act: -0.0001

Data Index: 121979 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7671. Min Act: -0.0001

Data Index: 474677 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8369. Min Act: -0.0001

Data Index: 334402 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8123. Min Act: -0.0001

Data Index: 1138062 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8314. Min Act: -0.0001

Data Index: 361414 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8306. Min Act: -0.0001

Data Index: 865228 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7995. Min Act: -0.0001

Data Index: 386755 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8469. Min Act: -0.0001

Data Index: 152936 (C4 (Web Text))

Max Activating Token Index: 956