Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 730 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.3056. Min Act: -0.1700

Data Index: 1097794 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.2271. Min Act: -0.1700

Data Index: 128624 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.2113. Min Act: -0.1700

Data Index: 1271894 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.2113. Min Act: -0.1700

Data Index: 685284 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.1956. Min Act: -0.1700

Data Index: 524608 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.2113. Min Act: -0.1700

Data Index: 1191032 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.1484. Min Act: -0.1700

Data Index: 1063883 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.1799. Min Act: -0.1700

Data Index: 753026 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0853. Min Act: -0.1700

Data Index: 980486 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0696. Min Act: -0.1700

Data Index: 1130375 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0853. Min Act: -0.1700

Data Index: 347081 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.1169. Min Act: -0.1700

Data Index: 802729 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0538. Min Act: -0.1700

Data Index: 77219 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0380. Min Act: -0.1700

Data Index: 253534 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0696. Min Act: -0.1700

Data Index: 534372 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0696. Min Act: -0.1700

Data Index: 863367 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0538. Min Act: -0.1700

Data Index: 1083901 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0222. Min Act: -0.1700

Data Index: 135283 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.1011. Min Act: -0.1700

Data Index: 1106396 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 3.3056. Min Range: -3.3056

Max Act: 3.0380. Min Act: -0.1700

Data Index: 158385 (C4 (Web Text))

Max Activating Token Index: 292