Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1735 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.2665. Min Act: -0.0001

Data Index: 32548 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.3134. Min Act: -0.0001

Data Index: 855666 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0315. Min Act: -0.0001

Data Index: 182953 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9403. Min Act: -0.0001

Data Index: 518900 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9816. Min Act: -0.0001

Data Index: 244679 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9163. Min Act: -0.0001

Data Index: 194870 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9469. Min Act: -0.0001

Data Index: 255265 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.8964. Min Act: -0.0001

Data Index: 120602 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9218. Min Act: -0.0001

Data Index: 1420365 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0176. Min Act: -0.0001

Data Index: 755308 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9090. Min Act: -0.0001

Data Index: 1114809 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.8685. Min Act: -0.0001

Data Index: 204169 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.8947. Min Act: -0.0001

Data Index: 902139 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9032. Min Act: -0.0001

Data Index: 199996 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9024. Min Act: -0.0001

Data Index: 407507 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9627. Min Act: -0.0001

Data Index: 723018 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1274076 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.8253. Min Act: -0.0001

Data Index: 107339 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.8765. Min Act: -0.0001

Data Index: 740847 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.8500. Min Act: -0.0001

Data Index: 645040 (C4 (Web Text))

Max Activating Token Index: 420