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

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

Neuron 1624 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: 3.6703. Min Range: -3.6703

Max Act: 3.6703. Min Act: -0.1700

Data Index: 1160969 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.6703. Min Act: -0.1700

Data Index: 370442 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.6390. Min Act: -0.1700

Data Index: 690585 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.6076. Min Act: -0.1700

Data Index: 899750 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.6390. Min Act: -0.1700

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.6076. Min Act: -0.1700

Data Index: 1308213 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.6076. Min Act: -0.1700

Data Index: 461273 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.6076. Min Act: -0.1700

Data Index: 340021 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4823. Min Act: -0.1700

Data Index: 387007 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.5137. Min Act: -0.1700

Data Index: 992687 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.5450. Min Act: -0.1700

Data Index: 498229 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4823. Min Act: -0.1700

Data Index: 1353331 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4823. Min Act: -0.1700

Data Index: 685274 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4823. Min Act: -0.1700

Data Index: 554926 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.5137. Min Act: -0.1700

Data Index: 207942 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4823. Min Act: -0.1700

Data Index: 651134 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4823. Min Act: -0.1700

Data Index: 573335 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4823. Min Act: -0.1700

Data Index: 1166583 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4510. Min Act: -0.1700

Data Index: 734235 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 3.6703. Min Range: -3.6703

Max Act: 3.4196. Min Act: -0.1700

Data Index: 1203571 (C4 (Web Text))

Max Activating Token Index: 50