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

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

Neuron 1856 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.3904. Min Act: -0.0001

Data Index: 1568741 (Python Code)

Max Activating Token Index: 580

Text #1

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.3414. Min Act: -0.0001

Data Index: 1582000 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2178. Min Act: -0.0001

Data Index: 1458106 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2755. Min Act: -0.0001

Data Index: 1579851 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2313. Min Act: -0.0001

Data Index: 1488274 (Python Code)

Max Activating Token Index: 986

Text #5

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2550. Min Act: -0.0001

Data Index: 1633337 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.3343. Min Act: -0.0001

Data Index: 1397365 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.1947. Min Act: -0.0001

Data Index: 1371354 (Python Code)

Max Activating Token Index: 936

Text #8

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2412. Min Act: -0.0001

Data Index: 1467733 (Python Code)

Max Activating Token Index: 985

Text #9

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.1640. Min Act: -0.0001

Data Index: 1638545 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.0736. Min Act: -0.0001

Data Index: 1492361 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2193. Min Act: -0.0001

Data Index: 1446886 (Python Code)

Max Activating Token Index: 116

Text #12

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2315. Min Act: -0.0001

Data Index: 1507230 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2106. Min Act: -0.0001

Data Index: 1512323 (Python Code)

Max Activating Token Index: 946

Text #14

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2875. Min Act: -0.0001

Data Index: 1385022 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.1343. Min Act: -0.0001

Data Index: 1413958 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.1973. Min Act: -0.0001

Data Index: 1369421 (Python Code)

Max Activating Token Index: 100

Text #17

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.1610. Min Act: -0.0001

Data Index: 1467575 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.2185. Min Act: -0.0001

Data Index: 1645657 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 1.3904. Min Range: -1.3904

Max Act: 1.1826. Min Act: -0.0001

Data Index: 1594479 (Python Code)

Max Activating Token Index: 577