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

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

Neuron 3435 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: 0.1369. Min Range: -0.1369

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1640525 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1547294 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1567563 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1583538 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1495265 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1536393 (Python Code)

Max Activating Token Index: 142

Text #6

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1514474 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1622212 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1391789 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1419603 (Python Code)

Max Activating Token Index: 68

Text #10

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1478097 (Python Code)

Max Activating Token Index: 423

Text #11

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1629953 (Python Code)

Max Activating Token Index: 317

Text #12

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1448498 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1415612 (Python Code)

Max Activating Token Index: 279

Text #14

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1573360 (Python Code)

Max Activating Token Index: 262

Text #15

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1420764 (Python Code)

Max Activating Token Index: 82

Text #16

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1470678 (Python Code)

Max Activating Token Index: 172

Text #17

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1380533 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1568081 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1653382 (Python Code)

Max Activating Token Index: 35