Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1011 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.1228. Min Range: -7.1228

Max Act: 7.1228. Min Act: -0.1700

Data Index: 1411065 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 7.1228. Min Range: -7.1228

Max Act: 7.0603. Min Act: -0.1700

Data Index: 1550133 (Python Code)

Max Activating Token Index: 837

Text #2

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9665. Min Act: -0.1700

Data Index: 1375953 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9665. Min Act: -0.1700

Data Index: 1492436 (Python Code)

Max Activating Token Index: 135

Text #4

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9978. Min Act: -0.1700

Data Index: 1463710 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9040. Min Act: -0.1700

Data Index: 1444645 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9665. Min Act: -0.1700

Data Index: 1599828 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9353. Min Act: -0.1700

Data Index: 1639772 (Python Code)

Max Activating Token Index: 356

Text #8

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8728. Min Act: -0.1700

Data Index: 1375431 (Python Code)

Max Activating Token Index: 821

Text #9

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9353. Min Act: -0.1700

Data Index: 1547182 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8103. Min Act: -0.1700

Data Index: 1477921 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8415. Min Act: -0.1700

Data Index: 1634939 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8415. Min Act: -0.1700

Data Index: 1484528 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8103. Min Act: -0.1700

Data Index: 1492311 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9040. Min Act: -0.1700

Data Index: 1407334 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.9353. Min Act: -0.1700

Data Index: 1606318 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8415. Min Act: -0.1700

Data Index: 1574485 (Python Code)

Max Activating Token Index: 112

Text #17

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8728. Min Act: -0.1700

Data Index: 1523467 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8415. Min Act: -0.1700

Data Index: 1380622 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 7.1228. Min Range: -7.1228

Max Act: 6.8728. Min Act: -0.1700

Data Index: 1611117 (Python Code)

Max Activating Token Index: 772