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

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

Neuron 3349 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2937. Min Act: -0.0000

Data Index: 892231 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2940. Min Act: -0.0000

Data Index: 241505 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2689. Min Act: -0.0000

Data Index: 419212 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2368. Min Act: -0.0000

Data Index: 349237 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2472. Min Act: -0.0000

Data Index: 240435 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2466. Min Act: -0.0001

Data Index: 890902 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2248. Min Act: -0.0001

Data Index: 870848 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2244. Min Act: -0.0000

Data Index: 718838 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1005929 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1986. Min Act: -0.0000

Data Index: 490961 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2039. Min Act: -0.0001

Data Index: 471095 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1944. Min Act: -0.0001

Data Index: 511624 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1992. Min Act: -0.0001

Data Index: 783271 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1989. Min Act: -0.0001

Data Index: 778220 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2053. Min Act: -0.0001

Data Index: 273064 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2124. Min Act: -0.0000

Data Index: 20877 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1008813 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1838. Min Act: -0.0001

Data Index: 401792 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1954. Min Act: -0.0001

Data Index: 56683 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1168717 (C4 (Web Text))

Max Activating Token Index: 67