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

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

Neuron 182 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: 7.0388. Min Range: -7.0388

Max Act: 7.0388. Min Act: -0.1700

Data Index: 1128135 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.9763. Min Act: -0.1700

Data Index: 1013397 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.9138. Min Act: -0.1700

Data Index: 526183 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.9138. Min Act: -0.1700

Data Index: 650677 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.9138. Min Act: -0.1700

Data Index: 84719 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.9138. Min Act: -0.1700

Data Index: 957251 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.8825. Min Act: -0.1700

Data Index: 102717 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.8825. Min Act: -0.1700

Data Index: 752253 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.8825. Min Act: -0.1700

Data Index: 209064 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.8200. Min Act: -0.1700

Data Index: 1151172 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7888. Min Act: -0.1700

Data Index: 545545 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7888. Min Act: -0.1700

Data Index: 36853 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7888. Min Act: -0.1700

Data Index: 890300 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7888. Min Act: -0.1700

Data Index: 132638 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7888. Min Act: -0.1700

Data Index: 780362 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7888. Min Act: -0.1700

Data Index: 887608 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7888. Min Act: -0.1700

Data Index: 785402 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7575. Min Act: -0.1700

Data Index: 729910 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7263. Min Act: -0.1700

Data Index: 931454 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 7.0388. Min Range: -7.0388

Max Act: 6.7575. Min Act: -0.1700

Data Index: 448816 (C4 (Web Text))

Max Activating Token Index: 1002