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

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

Neuron 1244 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: 3.7239. Min Range: -3.7239

Max Act: 3.7239. Min Act: -0.1700

Data Index: 789425 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.4734. Min Act: -0.1700

Data Index: 315124 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.4577. Min Act: -0.1700

Data Index: 1291884 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3950. Min Act: -0.1700

Data Index: 781192 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3322. Min Act: -0.1700

Data Index: 422159 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1188231 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3165. Min Act: -0.1700

Data Index: 315832 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3165. Min Act: -0.1700

Data Index: 502977 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3165. Min Act: -0.1700

Data Index: 182807 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1297792 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3008. Min Act: -0.1700

Data Index: 1152813 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.3008. Min Act: -0.1700

Data Index: 381694 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2851. Min Act: -0.1700

Data Index: 1129309 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2851. Min Act: -0.1700

Data Index: 1159253 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2851. Min Act: -0.1700

Data Index: 1228954 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2537. Min Act: -0.1700

Data Index: 1300543 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2694. Min Act: -0.1700

Data Index: 801910 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2694. Min Act: -0.1700

Data Index: 1297508 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2694. Min Act: -0.1700

Data Index: 323732 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 3.7239. Min Range: -3.7239

Max Act: 3.2537. Min Act: -0.1700

Data Index: 1328303 (C4 (Web Text))

Max Activating Token Index: 129