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

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

Neuron 4574 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: 0.6985. Min Range: -0.6985

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1512855 (Python Code)

Max Activating Token Index: 821

Text #1

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6886. Min Act: -0.0001

Data Index: 1448697 (Python Code)

Max Activating Token Index: 940

Text #2

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6648. Min Act: -0.0001

Data Index: 1461551 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6599. Min Act: -0.0001

Data Index: 1477441 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1652697 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1439803 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6389. Min Act: -0.0001

Data Index: 1386020 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1410277 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6256. Min Act: -0.0001

Data Index: 1458622 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1542421 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6403. Min Act: -0.0001

Data Index: 1565463 (Python Code)

Max Activating Token Index: 814

Text #11

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6311. Min Act: -0.0001

Data Index: 1632809 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6312. Min Act: -0.0001

Data Index: 1517582 (Python Code)

Max Activating Token Index: 731

Text #13

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6246. Min Act: -0.0001

Data Index: 1637048 (Python Code)

Max Activating Token Index: 859

Text #14

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6313. Min Act: -0.0001

Data Index: 1415145 (Python Code)

Max Activating Token Index: 662

Text #15

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1402409 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1464437 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6169. Min Act: -0.0001

Data Index: 1421618 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1634474 (Python Code)

Max Activating Token Index: 601

Text #19

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1547097 (Python Code)

Max Activating Token Index: 866