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

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

Neuron 3681 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: 1.0552. Min Range: -1.0552

Max Act: 0.9888. Min Act: -0.0001

Data Index: 183074 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.0552. Min Range: -1.0552

Max Act: 1.0552. Min Act: -0.0000

Data Index: 584191 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.9364. Min Act: -0.0001

Data Index: 15382 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.9244. Min Act: -0.0001

Data Index: 885959 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.9560. Min Act: -0.0001

Data Index: 366808 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8660. Min Act: -0.0001

Data Index: 1098518 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.9309. Min Act: -0.0001

Data Index: 588747 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8713. Min Act: -0.0001

Data Index: 648595 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8890. Min Act: -0.0001

Data Index: 990840 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.9184. Min Act: -0.0001

Data Index: 70891 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8952. Min Act: -0.0001

Data Index: 524411 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1175233 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8746. Min Act: -0.0001

Data Index: 492103 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1255423 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8778. Min Act: -0.0001

Data Index: 961381 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8823. Min Act: -0.0001

Data Index: 397005 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1006826 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8298. Min Act: -0.0001

Data Index: 1351609 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8048. Min Act: -0.0001

Data Index: 152720 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1035721 (C4 (Web Text))

Max Activating Token Index: 931