Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 998 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0183. Min Range: -1.0183

Max Act: 1.0183. Min Act: -0.0001

Data Index: 640618 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.0183. Min Range: -1.0183

Max Act: 1.0131. Min Act: -0.0001

Data Index: 246953 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.9986. Min Act: -0.0001

Data Index: 324355 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.9446. Min Act: -0.0001

Data Index: 819502 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1197844 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8559. Min Act: -0.0001

Data Index: 142546 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8193. Min Act: -0.0001

Data Index: 365120 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1131451 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7894. Min Act: -0.0001

Data Index: 297051 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8200. Min Act: -0.0001

Data Index: 562982 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8378. Min Act: -0.0001

Data Index: 1039788 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6858. Min Act: -0.0001

Data Index: 277049 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8273. Min Act: -0.0001

Data Index: 1124150 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8024. Min Act: -0.0001

Data Index: 656001 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7636. Min Act: -0.0001

Data Index: 392795 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7392. Min Act: -0.0001

Data Index: 183241 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7335. Min Act: -0.0001

Data Index: 805082 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8021. Min Act: -0.0001

Data Index: 1162195 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7984. Min Act: -0.0001

Data Index: 344084 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7575. Min Act: -0.0001

Data Index: 173538 (C4 (Web Text))

Max Activating Token Index: 877