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

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

Neuron 812 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: 0.2600. Min Range: -0.2600

Max Act: 0.2600. Min Act: -0.0000

Data Index: 903173 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1136557 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2330. Min Act: -0.0001

Data Index: 435448 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2273. Min Act: -0.0001

Data Index: 898950 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2060. Min Act: -0.0000

Data Index: 467885 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2170. Min Act: -0.0000

Data Index: 253340 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1046655 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2141. Min Act: -0.0000

Data Index: 974055 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2120. Min Act: -0.0001

Data Index: 119030 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2119. Min Act: -0.0001

Data Index: 491867 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1922. Min Act: -0.0001

Data Index: 694567 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1588 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2041. Min Act: -0.0000

Data Index: 465758 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1922. Min Act: -0.0000

Data Index: 741010 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1847. Min Act: -0.0000

Data Index: 825372 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1987. Min Act: -0.0001

Data Index: 924136 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1263670 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1970. Min Act: -0.0000

Data Index: 819481 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1967. Min Act: -0.0000

Data Index: 442671 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1232197 (C4 (Web Text))

Max Activating Token Index: 572