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

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

Neuron 55 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: 3.4952. Min Range: -3.4952

Max Act: 3.4952. Min Act: -0.1700

Data Index: 1094934 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4325. Min Act: -0.1700

Data Index: 1336640 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4169. Min Act: -0.1700

Data Index: 1653191 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3698. Min Act: -0.1700

Data Index: 350622 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3855. Min Act: -0.1700

Data Index: 1128379 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3698. Min Act: -0.1700

Data Index: 290340 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3855. Min Act: -0.1700

Data Index: 5179 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3698. Min Act: -0.1700

Data Index: 948993 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3698. Min Act: -0.1700

Data Index: 828261 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 843626 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 13591 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 1150134 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 689420 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3384. Min Act: -0.1700

Data Index: 1202540 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 1088404 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 423044 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3698. Min Act: -0.1700

Data Index: 1236993 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3384. Min Act: -0.1700

Data Index: 388695 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 1299743 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3541. Min Act: -0.1700

Data Index: 1318764 (C4 (Web Text))

Max Activating Token Index: 5