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

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

Neuron 881 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: 5.3458. Min Range: -5.3458

Max Act: 5.3458. Min Act: -0.1700

Data Index: 142610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.3458. Min Range: -5.3458

Max Act: 5.1270. Min Act: -0.1698

Data Index: 1250187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.9395. Min Act: -0.1700

Data Index: 134687 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.8458. Min Act: -0.1698

Data Index: 298598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.8145. Min Act: -0.1700

Data Index: 583581 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.8145. Min Act: -0.1700

Data Index: 1079743 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.7208. Min Act: -0.1700

Data Index: 1037815 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.7208. Min Act: -0.1700

Data Index: 266612 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.7208. Min Act: -0.1700

Data Index: 1223046 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.7208. Min Act: -0.1700

Data Index: 1185644 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.7208. Min Act: -0.1700

Data Index: 40428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.7520. Min Act: -0.1673

Data Index: 473793 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6583. Min Act: -0.1700

Data Index: 438467 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6583. Min Act: -0.1700

Data Index: 1238708 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6895. Min Act: -0.0381

Data Index: 360046 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6583. Min Act: -0.1700

Data Index: 1106599 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6583. Min Act: -0.1700

Data Index: 402531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6895. Min Act: -0.1700

Data Index: 420818 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6583. Min Act: -0.1700

Data Index: 469792 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.3458. Min Range: -5.3458

Max Act: 4.6583. Min Act: -0.1696

Data Index: 105886 (C4 (Web Text))

Max Activating Token Index: 1023