Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3641 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6961. Min Act: -0.0001

Data Index: 465768 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1159141 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1132709 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5039. Min Act: -0.0000

Data Index: 943316 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1302217 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4939. Min Act: -0.0000

Data Index: 489262 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4344. Min Act: -0.0000

Data Index: 657363 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4473. Min Act: -0.0000

Data Index: 51407 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4357. Min Act: -0.0001

Data Index: 972243 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1298983 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.3986. Min Act: -0.0000

Data Index: 481009 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.3867. Min Act: -0.0000

Data Index: 882610 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1215947 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1218974 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4952. Min Act: -0.0000

Data Index: 907800 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4051. Min Act: -0.0001

Data Index: 1208742 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4054. Min Act: -0.0000

Data Index: 719448 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.3853. Min Act: -0.0001

Data Index: 1244060 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.3702. Min Act: -0.0001

Data Index: 1174173 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.3967. Min Act: -0.0001

Data Index: 288282 (C4 (Web Text))

Max Activating Token Index: 366