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

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

Neuron 1140 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: 3.4438. Min Range: -3.4438

Max Act: 3.4438. Min Act: -0.1700

Data Index: 920448 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.4124. Min Act: -0.1700

Data Index: 369713 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1178458 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3811. Min Act: -0.1700

Data Index: 1097684 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3811. Min Act: -0.1700

Data Index: 247820 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 1139089 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 653002 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3811. Min Act: -0.1700

Data Index: 769969 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 372761 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3811. Min Act: -0.1700

Data Index: 537665 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 1025314 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 403902 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 439389 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 1078240 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3497. Min Act: -0.1700

Data Index: 336900 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3183. Min Act: -0.1700

Data Index: 231306 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3497. Min Act: -0.1700

Data Index: 943102 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3497. Min Act: -0.1700

Data Index: 1021992 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3497. Min Act: -0.1700

Data Index: 847994 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3497. Min Act: -0.1700

Data Index: 455036 (C4 (Web Text))

Max Activating Token Index: 23