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

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

Neuron 1978 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.8312. Min Act: -0.1700

Data Index: 1109292 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7843. Min Act: -0.1700

Data Index: 31258 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7687. Min Act: -0.1700

Data Index: 100443 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7530. Min Act: -0.1700

Data Index: 805583 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7687. Min Act: -0.1700

Data Index: 572103 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7217. Min Act: -0.1700

Data Index: 477594 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7217. Min Act: -0.1700

Data Index: 726601 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6905. Min Act: -0.1700

Data Index: 794232 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7061. Min Act: -0.1700

Data Index: 847913 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7061. Min Act: -0.1700

Data Index: 883013 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7061. Min Act: -0.1700

Data Index: 438079 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6748. Min Act: -0.1700

Data Index: 900290 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7061. Min Act: -0.1700

Data Index: 919361 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6748. Min Act: -0.1700

Data Index: 1319421 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6592. Min Act: -0.1700

Data Index: 112078 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6905. Min Act: -0.1700

Data Index: 880204 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6748. Min Act: -0.1700

Data Index: 988069 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6592. Min Act: -0.1700

Data Index: 1009510 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6748. Min Act: -0.1700

Data Index: 835725 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6592. Min Act: -0.1700

Data Index: 210362 (C4 (Web Text))

Max Activating Token Index: 471