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

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

Neuron 1707 in Layer 1

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: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1380047 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1362321 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1400938 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1371390 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1394312 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1375169 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1366126 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1386240 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1369149 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1402524 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1391724 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1395376 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1384944 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1360096 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1375941 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1407032 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1389402 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1379109 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1369423 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1389085 (Python Code)

Max Activating Token Index: 1