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

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

Neuron 2601 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: 0.2600. Min Range: -0.2600

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1335531 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2385. Min Act: -0.0001

Data Index: 668357 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1036443 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2325. Min Act: -0.0001

Data Index: 905236 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2249. Min Act: -0.0001

Data Index: 251096 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2254. Min Act: -0.0001

Data Index: 608562 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1079725 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2168. Min Act: -0.0001

Data Index: 970462 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2141. Min Act: -0.0001

Data Index: 622541 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2123. Min Act: -0.0001

Data Index: 931025 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2105. Min Act: -0.0001

Data Index: 1145992 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2172. Min Act: -0.0001

Data Index: 399202 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2189. Min Act: -0.0001

Data Index: 887064 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2048. Min Act: -0.0001

Data Index: 439664 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1957. Min Act: -0.0001

Data Index: 61267 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1994. Min Act: -0.0001

Data Index: 302254 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2014. Min Act: -0.0001

Data Index: 789925 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1944. Min Act: -0.0001

Data Index: 6674 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1794. Min Act: -0.0001

Data Index: 660009 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1559 (C4 (Web Text))

Max Activating Token Index: 825