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

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

Neuron 1552 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: 0.2706. Min Range: -0.2706

Max Act: 0.2587. Min Act: -0.0001

Data Index: 1441210 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2706. Min Act: -0.0001

Data Index: 1652884 (Python Code)

Max Activating Token Index: 538

Text #2

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2505. Min Act: -0.0001

Data Index: 998289 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1404226 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2253. Min Act: -0.0001

Data Index: 1557413 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1594972 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1391891 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2171. Min Act: -0.0001

Data Index: 1441985 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1426551 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1503819 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2194. Min Act: -0.0001

Data Index: 506457 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1569093 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1542229 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1533290 (Python Code)

Max Activating Token Index: 869

Text #14

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1651295 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2067. Min Act: -0.0001

Data Index: 1427387 (Python Code)

Max Activating Token Index: 939

Text #16

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1383228 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1591377 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1432444 (Python Code)

Max Activating Token Index: 433

Text #19

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1516664 (Python Code)

Max Activating Token Index: 164