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

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

Neuron 4350 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1151101 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.8566. Min Act: -0.0000

Data Index: 551560 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1002556 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.7477. Min Act: -0.0000

Data Index: 466632 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5287. Min Act: -0.0000

Data Index: 307543 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.8803. Min Act: -0.0000

Data Index: 768879 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.6802. Min Act: -0.0000

Data Index: 974755 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5061. Min Act: -0.0000

Data Index: 796462 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.6593. Min Act: -0.0000

Data Index: 537079 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5708. Min Act: -0.0000

Data Index: 683000 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5534. Min Act: -0.0000

Data Index: 657070 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.6359. Min Act: -0.0000

Data Index: 514972 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.6281. Min Act: -0.0000

Data Index: 553748 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5288. Min Act: -0.0000

Data Index: 498177 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.4975. Min Act: -0.0000

Data Index: 473260 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5787. Min Act: -0.0000

Data Index: 416957 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5566. Min Act: -0.0000

Data Index: 640608 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.6155. Min Act: -0.0000

Data Index: 1324969 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5118. Min Act: -0.0000

Data Index: 866711 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5070. Min Act: -0.0000

Data Index: 1273952 (C4 (Web Text))

Max Activating Token Index: 837