Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3255 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.7129. Min Act: -0.0001

Data Index: 1412800 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.4845. Min Act: -0.0001

Data Index: 1632104 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.5686. Min Act: -0.0001

Data Index: 1400220 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.4312. Min Act: -0.0002

Data Index: 1493984 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.3667. Min Act: -0.0001

Data Index: 1380937 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.3356. Min Act: -0.0002

Data Index: 1500207 (Python Code)

Max Activating Token Index: 410

Text #6

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.3398. Min Act: -0.0001

Data Index: 1629216 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.3569. Min Act: -0.0001

Data Index: 1510180 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2656. Min Act: -0.0001

Data Index: 1503113 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.3679. Min Act: -0.0001

Data Index: 1610279 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2903. Min Act: -0.0001

Data Index: 1551436 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2940. Min Act: -0.0001

Data Index: 1623699 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.3037. Min Act: -0.0002

Data Index: 1585062 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2262. Min Act: -0.0001

Data Index: 1623005 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2278. Min Act: -0.0001

Data Index: 1598856 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2738. Min Act: -0.0002

Data Index: 1628508 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2559. Min Act: -0.0001

Data Index: 1384608 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.3197. Min Act: -0.0001

Data Index: 1531706 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2137. Min Act: -0.0001

Data Index: 1586478 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 3.7129. Min Range: -3.7129

Max Act: 3.2681. Min Act: -0.0001

Data Index: 1545921 (Python Code)

Max Activating Token Index: 1007