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

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

Neuron 1293 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.6145. Min Act: -0.1700

Data Index: 1128257 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5675. Min Act: -0.1700

Data Index: 1190662 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5519. Min Act: -0.1700

Data Index: 200293 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5362. Min Act: -0.1700

Data Index: 265496 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5519. Min Act: -0.1700

Data Index: 1301270 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5206. Min Act: -0.1700

Data Index: 368626 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5206. Min Act: -0.1700

Data Index: 240710 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4892. Min Act: -0.1700

Data Index: 146918 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5206. Min Act: -0.1700

Data Index: 1346101 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5049. Min Act: -0.1700

Data Index: 25372 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5049. Min Act: -0.1700

Data Index: 123045 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5049. Min Act: -0.1700

Data Index: 281487 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5362. Min Act: -0.1700

Data Index: 402883 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4579. Min Act: -0.1700

Data Index: 1287337 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4892. Min Act: -0.1700

Data Index: 153243 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4892. Min Act: -0.1700

Data Index: 1243489 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4579. Min Act: -0.1700

Data Index: 464076 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4579. Min Act: -0.1700

Data Index: 300766 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4579. Min Act: -0.1700

Data Index: 524439 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4579. Min Act: -0.1700

Data Index: 364130 (C4 (Web Text))

Max Activating Token Index: 801