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

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

Neuron 253 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: 3.7238. Min Range: -3.7238

Max Act: 3.7238. Min Act: -0.1700

Data Index: 1324772 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6612. Min Act: -0.1700

Data Index: 1143777 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6612. Min Act: -0.1700

Data Index: 719311 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6299. Min Act: -0.1700

Data Index: 83391 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6299. Min Act: -0.1700

Data Index: 769766 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6299. Min Act: -0.1700

Data Index: 1143131 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6299. Min Act: -0.1700

Data Index: 336021 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 837652 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6299. Min Act: -0.1700

Data Index: 1326388 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 559231 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6299. Min Act: -0.1700

Data Index: 802829 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 820766 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 533791 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 171856 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 682097 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 1346220 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5673. Min Act: -0.1700

Data Index: 1333131 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5986. Min Act: -0.1700

Data Index: 1270112 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6299. Min Act: -0.1700

Data Index: 684618 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5360. Min Act: -0.1700

Data Index: 133287 (C4 (Web Text))

Max Activating Token Index: 502