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

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

Neuron 1168 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: 0.2801. Min Range: -0.2801

Max Act: 0.2801. Min Act: -0.0001

Data Index: 450293 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2555. Min Act: -0.0000

Data Index: 619399 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2298. Min Act: -0.0001

Data Index: 336592 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1087619 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1327139 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2187. Min Act: -0.0001

Data Index: 435259 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1263094 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2128. Min Act: -0.0001

Data Index: 214565 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2192. Min Act: -0.0001

Data Index: 606914 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2115. Min Act: -0.0001

Data Index: 599782 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2061. Min Act: -0.0000

Data Index: 318321 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2034. Min Act: -0.0000

Data Index: 7444 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2101. Min Act: -0.0000

Data Index: 754459 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2018. Min Act: -0.0001

Data Index: 256287 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1062813 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1111881 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1211345 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1245424 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2036. Min Act: -0.0001

Data Index: 328371 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1840. Min Act: -0.0001

Data Index: 457264 (C4 (Web Text))

Max Activating Token Index: 81