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

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

Neuron 1096 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: 3.8281. Min Range: -3.8281

Max Act: 3.8281. Min Act: -0.1700

Data Index: 961831 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.7655. Min Act: -0.1700

Data Index: 1236639 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.7968. Min Act: -0.1700

Data Index: 432145 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.7655. Min Act: -0.1700

Data Index: 1095032 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.7029. Min Act: -0.1700

Data Index: 934821 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.7342. Min Act: -0.1700

Data Index: 305467 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.7029. Min Act: -0.1700

Data Index: 1137880 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.7029. Min Act: -0.1700

Data Index: 1101634 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6716. Min Act: -0.1700

Data Index: 1213982 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6716. Min Act: -0.1700

Data Index: 164046 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6716. Min Act: -0.1700

Data Index: 180263 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6403. Min Act: -0.1700

Data Index: 247029 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6090. Min Act: -0.1700

Data Index: 1121248 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6403. Min Act: -0.1700

Data Index: 133304 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6716. Min Act: -0.1700

Data Index: 1235223 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6403. Min Act: -0.1700

Data Index: 862706 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.5777. Min Act: -0.1700

Data Index: 539849 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6090. Min Act: -0.1700

Data Index: 537819 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.5777. Min Act: -0.1700

Data Index: 326623 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 3.8281. Min Range: -3.8281

Max Act: 3.6090. Min Act: -0.1700

Data Index: 1018318 (C4 (Web Text))

Max Activating Token Index: 740