Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 439 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.9757. Min Act: -0.1700

Data Index: 539662 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.8975. Min Act: -0.1700

Data Index: 1122632 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.8506. Min Act: -0.1700

Data Index: 1461551 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.8037. Min Act: -0.1700

Data Index: 1459991 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.8350. Min Act: -0.1700

Data Index: 741141 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7881. Min Act: -0.1700

Data Index: 298017 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7568. Min Act: -0.1700

Data Index: 1409977 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7568. Min Act: -0.1700

Data Index: 1464437 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7255. Min Act: -0.1700

Data Index: 204287 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7255. Min Act: -0.1700

Data Index: 1516039 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7255. Min Act: -0.1700

Data Index: 1498340 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6942. Min Act: -0.1700

Data Index: 1482442 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7255. Min Act: -0.1700

Data Index: 1591639 (Python Code)

Max Activating Token Index: 130

Text #13

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6942. Min Act: -0.1700

Data Index: 1421618 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6786. Min Act: -0.1700

Data Index: 1632809 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7724. Min Act: -0.1700

Data Index: 1148738 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6629. Min Act: -0.1700

Data Index: 1369500 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.7099. Min Act: -0.1700

Data Index: 192236 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6629. Min Act: -0.1700

Data Index: 1482680 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 3.9757. Min Range: -3.9757

Max Act: 3.6786. Min Act: -0.1700

Data Index: 1420577 (Python Code)

Max Activating Token Index: 177