Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2730 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.4139. Min Act: -0.0002

Data Index: 1207151 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2955. Min Act: -0.0002

Data Index: 379707 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2866. Min Act: -0.0002

Data Index: 205209 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2517. Min Act: -0.0002

Data Index: 1194502 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2415. Min Act: -0.0002

Data Index: 1094178 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2429. Min Act: -0.0002

Data Index: 40157 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2021. Min Act: -0.0002

Data Index: 967425 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2109. Min Act: -0.0002

Data Index: 1042140 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2149. Min Act: -0.0002

Data Index: 130380 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2039. Min Act: -0.0003

Data Index: 1137311 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2056. Min Act: -0.0002

Data Index: 313904 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1946. Min Act: -0.0002

Data Index: 347247 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1943. Min Act: -0.0002

Data Index: 919330 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1938. Min Act: -0.0002

Data Index: 442533 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1705. Min Act: -0.0002

Data Index: 1233601 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1989. Min Act: -0.0002

Data Index: 1043017 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1731. Min Act: -0.0002

Data Index: 710270 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1971. Min Act: -0.0002

Data Index: 709944 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2064. Min Act: -0.0002

Data Index: 606115 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1563. Min Act: -0.0003

Data Index: 889878 (C4 (Web Text))

Max Activating Token Index: 202