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

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

Neuron 486 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5383. Min Range: -6.5383

Max Act: 6.5383. Min Act: -0.0000

Data Index: 987163 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 6.5383. Min Range: -6.5383

Max Act: 5.2086. Min Act: -0.0000

Data Index: 1095822 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.8447. Min Act: -0.0000

Data Index: 1315823 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.9034. Min Act: -0.0000

Data Index: 709035 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.6311. Min Act: -0.0000

Data Index: 1054867 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.5954. Min Act: -0.0000

Data Index: 455514 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.2804. Min Act: -0.0000

Data Index: 637763 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.2939. Min Act: -0.0000

Data Index: 684780 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.3168. Min Act: -0.0000

Data Index: 805417 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.3163. Min Act: -0.0000

Data Index: 1199348 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.3151. Min Act: -0.0000

Data Index: 802935 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.3541. Min Act: -0.0000

Data Index: 376416 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.3631. Min Act: -0.0000

Data Index: 359356 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.1254. Min Act: -0.0000

Data Index: 1268671 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.0907. Min Act: -0.0000

Data Index: 1028093 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 6.5383. Min Range: -6.5383

Max Act: 3.9508. Min Act: -0.0000

Data Index: 712372 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 6.5383. Min Range: -6.5383

Max Act: 4.1204. Min Act: -0.0000

Data Index: 673741 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 6.5383. Min Range: -6.5383

Max Act: 3.7754. Min Act: -0.0000

Data Index: 57983 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 6.5383. Min Range: -6.5383

Max Act: 3.2709. Min Act: -0.0000

Data Index: 451097 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 6.5383. Min Range: -6.5383

Max Act: 3.9207. Min Act: -0.0000

Data Index: 732442 (C4 (Web Text))

Max Activating Token Index: 161