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

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

Neuron 3784 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.6685. Min Act: -0.0001

Data Index: 1232668 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5411. Min Act: -0.0001

Data Index: 791856 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.6773. Min Act: -0.0001

Data Index: 1034015 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.6965. Min Act: -0.0001

Data Index: 638869 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5598. Min Act: -0.0001

Data Index: 793001 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4333. Min Act: -0.0001

Data Index: 921932 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4715. Min Act: -0.0001

Data Index: 1579508 (Python Code)

Max Activating Token Index: 725

Text #7

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4394. Min Act: -0.0001

Data Index: 418190 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.6100. Min Act: -0.0001

Data Index: 924693 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3763. Min Act: -0.0001

Data Index: 290801 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3440. Min Act: -0.0001

Data Index: 1304774 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3901. Min Act: -0.0001

Data Index: 255662 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4203. Min Act: -0.0001

Data Index: 1248980 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3413. Min Act: -0.0001

Data Index: 111586 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3462. Min Act: -0.0001

Data Index: 1136732 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.2616. Min Act: -0.0001

Data Index: 794709 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3327. Min Act: -0.0001

Data Index: 148351 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3273. Min Act: -0.0001

Data Index: 1353429 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3699. Min Act: -0.0001

Data Index: 869397 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.2391. Min Act: -0.0001

Data Index: 56853 (C4 (Web Text))

Max Activating Token Index: 984