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

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

Neuron 5154 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: 1.6250. Min Range: -1.6250

Max Act: 1.6250. Min Act: -0.0002

Data Index: 1533814 (Python Code)

Max Activating Token Index: 87

Text #1

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5458. Min Act: -0.0002

Data Index: 1579958 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5451. Min Act: -0.0002

Data Index: 1605293 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5669. Min Act: -0.0002

Data Index: 1413399 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5079. Min Act: -0.0002

Data Index: 1369085 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5004. Min Act: -0.0002

Data Index: 1611375 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5090. Min Act: -0.0002

Data Index: 1562039 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5115. Min Act: -0.0002

Data Index: 1545944 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.4554. Min Act: -0.0002

Data Index: 1635463 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.5135. Min Act: -0.0002

Data Index: 1560489 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.4409. Min Act: -0.0002

Data Index: 1429767 (Python Code)

Max Activating Token Index: 459

Text #11

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.4505. Min Act: -0.0002

Data Index: 1475642 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.4595. Min Act: -0.0002

Data Index: 1477893 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3878. Min Act: -0.0002

Data Index: 1506762 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3784. Min Act: -0.0002

Data Index: 1403910 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.4293. Min Act: -0.0002

Data Index: 1542504 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.4363. Min Act: -0.0002

Data Index: 1597895 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3806. Min Act: -0.0002

Data Index: 1444387 (Python Code)

Max Activating Token Index: 103

Text #18

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3469. Min Act: -0.0002

Data Index: 1388566 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 1.6250. Min Range: -1.6250

Max Act: 1.3531. Min Act: -0.0002

Data Index: 1363374 (Python Code)

Max Activating Token Index: 247