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

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

Neuron 1542 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: 0.2610. Min Range: -0.2610

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1553373 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2610. Min Act: -0.0001

Data Index: 1546264 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2522. Min Act: -0.0001

Data Index: 153698 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1378025 (Python Code)

Max Activating Token Index: 656

Text #4

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2488. Min Act: -0.0001

Data Index: 885882 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2546. Min Act: -0.0001

Data Index: 1481147 (Python Code)

Max Activating Token Index: 513

Text #6

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2525. Min Act: -0.0001

Data Index: 321291 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1571456 (Python Code)

Max Activating Token Index: 141

Text #8

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1564166 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1405554 (Python Code)

Max Activating Token Index: 138

Text #10

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1532638 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1407912 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1446447 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1368071 (Python Code)

Max Activating Token Index: 179

Text #14

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1415625 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1096785 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1649485 (Python Code)

Max Activating Token Index: 766

Text #17

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2208. Min Act: -0.0001

Data Index: 735708 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1568971 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2167. Min Act: -0.0001

Data Index: 1464185 (Python Code)

Max Activating Token Index: 148