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

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

Neuron 1160 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.3341. Min Act: -0.1700

Data Index: 419855 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.3184. Min Act: -0.1700

Data Index: 582550 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.2399. Min Act: -0.1700

Data Index: 897235 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.2242. Min Act: -0.1700

Data Index: 1010584 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.2242. Min Act: -0.1700

Data Index: 1346280 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1927. Min Act: -0.1700

Data Index: 418370 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.2084. Min Act: -0.1700

Data Index: 1024934 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1927. Min Act: -0.1700

Data Index: 1292887 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1927. Min Act: -0.1700

Data Index: 992171 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1927. Min Act: -0.1700

Data Index: 1043303 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1927. Min Act: -0.1700

Data Index: 103838 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1770. Min Act: -0.1700

Data Index: 89055 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1927. Min Act: -0.1700

Data Index: 982939 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1927. Min Act: -0.1700

Data Index: 521269 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1770. Min Act: -0.1700

Data Index: 608990 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1770. Min Act: -0.1700

Data Index: 400062 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1612. Min Act: -0.1700

Data Index: 841013 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1455. Min Act: -0.1700

Data Index: 583664 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1455. Min Act: -0.1700

Data Index: 1112958 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 3.3341. Min Range: -3.3341

Max Act: 3.1612. Min Act: -0.1700

Data Index: 1082570 (C4 (Web Text))

Max Activating Token Index: 580