Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4851 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0226. Min Range: -1.0226

Max Act: 1.0226. Min Act: -0.0000

Data Index: 457319 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9439. Min Act: -0.0000

Data Index: 371907 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.0226. Min Range: -1.0226

Max Act: 1.0121. Min Act: -0.0000

Data Index: 634738 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9445. Min Act: -0.0000

Data Index: 755476 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9403. Min Act: -0.0000

Data Index: 788243 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9985. Min Act: -0.0000

Data Index: 844892 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9756. Min Act: -0.0000

Data Index: 299640 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1204390 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1359527 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9077. Min Act: -0.0000

Data Index: 882207 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9082. Min Act: -0.0000

Data Index: 72533 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8461. Min Act: -0.0000

Data Index: 871412 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8881. Min Act: -0.0000

Data Index: 377045 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8904. Min Act: -0.0000

Data Index: 971354 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8760. Min Act: -0.0000

Data Index: 711403 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8215. Min Act: -0.0000

Data Index: 627804 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8450. Min Act: -0.0000

Data Index: 836470 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.7957. Min Act: -0.0000

Data Index: 207989 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8231. Min Act: -0.0000

Data Index: 676019 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1059186 (C4 (Web Text))

Max Activating Token Index: 268