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

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

Neuron 614 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: 3.6978. Min Range: -3.6978

Max Act: 3.6978. Min Act: -0.1700

Data Index: 1119934 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.6195. Min Act: -0.1700

Data Index: 1208211 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.6352. Min Act: -0.1700

Data Index: 1342610 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.5882. Min Act: -0.1700

Data Index: 1129567 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.6038. Min Act: -0.1700

Data Index: 727066 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.5412. Min Act: -0.1700

Data Index: 80101 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4942. Min Act: -0.1700

Data Index: 795739 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.5099. Min Act: -0.1700

Data Index: 13165 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4942. Min Act: -0.1700

Data Index: 965394 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.5099. Min Act: -0.1700

Data Index: 235831 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4942. Min Act: -0.1700

Data Index: 684051 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4942. Min Act: -0.1700

Data Index: 752271 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4629. Min Act: -0.1700

Data Index: 1064123 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4629. Min Act: -0.1700

Data Index: 1160288 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4472. Min Act: -0.1700

Data Index: 1193389 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4629. Min Act: -0.1700

Data Index: 235987 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4472. Min Act: -0.1700

Data Index: 44362 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4315. Min Act: -0.1700

Data Index: 862062 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4472. Min Act: -0.1700

Data Index: 359292 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 3.6978. Min Range: -3.6978

Max Act: 3.4315. Min Act: -0.1700

Data Index: 440322 (C4 (Web Text))

Max Activating Token Index: 437