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

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

Neuron 832 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.9253. Min Act: -0.0001

Data Index: 548718 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.8924. Min Act: -0.0001

Data Index: 161770 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.8147. Min Act: -0.0001

Data Index: 1343439 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.8290. Min Act: -0.0001

Data Index: 495517 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1191687 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1504952 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7982. Min Act: -0.0001

Data Index: 1527293 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7715. Min Act: -0.0001

Data Index: 479548 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7711. Min Act: -0.0001

Data Index: 1652775 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7697. Min Act: -0.0001

Data Index: 1501766 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.8149. Min Act: -0.0001

Data Index: 545000 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7208. Min Act: -0.0001

Data Index: 499743 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6615. Min Act: -0.0001

Data Index: 228997 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7871. Min Act: -0.0001

Data Index: 72878 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7286. Min Act: -0.0001

Data Index: 1559810 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1638053 (Python Code)

Max Activating Token Index: 665

Text #16

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7501. Min Act: -0.0001

Data Index: 959845 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1028131 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7315. Min Act: -0.0001

Data Index: 1212413 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6101. Min Act: -0.0002

Data Index: 1109225 (C4 (Web Text))

Max Activating Token Index: 896