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

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

Neuron 1413 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.2600. Min Act: -0.1700

Data Index: 32163 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.1814. Min Act: -0.1700

Data Index: 993052 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0869. Min Act: -0.1700

Data Index: 861906 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0395. Min Act: -0.1700

Data Index: 468281 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0553. Min Act: -0.1700

Data Index: 256794 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.1026. Min Act: -0.1700

Data Index: 419215 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0237. Min Act: -0.1700

Data Index: 973212 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0395. Min Act: -0.1700

Data Index: 235504 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0237. Min Act: -0.1700

Data Index: 106741 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 3.2600. Min Range: -3.2600

Max Act: 2.9921. Min Act: -0.1700

Data Index: 872584 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0237. Min Act: -0.1700

Data Index: 478263 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 3.2600. Min Range: -3.2600

Max Act: 2.9763. Min Act: -0.1700

Data Index: 1071053 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 3.2600. Min Range: -3.2600

Max Act: 2.9763. Min Act: -0.1700

Data Index: 96900 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0079. Min Act: -0.1700

Data Index: 153262 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0079. Min Act: -0.1700

Data Index: 1602486 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 3.2600. Min Range: -3.2600

Max Act: 3.0079. Min Act: -0.1700

Data Index: 1535985 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 3.2600. Min Range: -3.2600

Max Act: 2.9921. Min Act: -0.1700

Data Index: 1041482 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 3.2600. Min Range: -3.2600

Max Act: 2.9288. Min Act: -0.1700

Data Index: 372486 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 3.2600. Min Range: -3.2600

Max Act: 2.9763. Min Act: -0.1700

Data Index: 883879 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 3.2600. Min Range: -3.2600

Max Act: 2.9921. Min Act: -0.1700

Data Index: 1496640 (Python Code)

Max Activating Token Index: 314