Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 48 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.3089. Min Act: -0.1700

Data Index: 7679180 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1611. Min Act: -0.1700

Data Index: 8717017 (Open Web Text)

Max Activating Token Index: 359

Text #2

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1609. Min Act: -0.1700

Data Index: 6378938 (Open Web Text)

Max Activating Token Index: 245

Text #3

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1229. Min Act: -0.1700

Data Index: 4673152 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1276. Min Act: -0.1700

Data Index: 235787 (Open Web Text)

Max Activating Token Index: 1004

Text #5

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1141. Min Act: -0.1700

Data Index: 4353946 (Open Web Text)

Max Activating Token Index: 646

Text #6

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0771. Min Act: -0.1700

Data Index: 4585979 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0851. Min Act: -0.1700

Data Index: 8292904 (Open Web Text)

Max Activating Token Index: 780

Text #8

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0620. Min Act: -0.1700

Data Index: 3719786 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0566. Min Act: -0.1700

Data Index: 5593306 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0425. Min Act: -0.1700

Data Index: 6051029 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0224. Min Act: -0.1700

Data Index: 718940 (Open Web Text)

Max Activating Token Index: 150

Text #12

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0177. Min Act: -0.1700

Data Index: 2880197 (Open Web Text)

Max Activating Token Index: 874

Text #13

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0005. Min Act: -0.1700

Data Index: 7282951 (Open Web Text)

Max Activating Token Index: 733

Text #14

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0048. Min Act: -0.1700

Data Index: 4452223 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0016. Min Act: -0.1700

Data Index: 2756665 (Open Web Text)

Max Activating Token Index: 712

Text #16

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0240. Min Act: -0.1700

Data Index: 5494106 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0039. Min Act: -0.1700

Data Index: 7420488 (Open Web Text)

Max Activating Token Index: 787

Text #18

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0043. Min Act: -0.1700

Data Index: 4951982 (Open Web Text)

Max Activating Token Index: 419

Text #19

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9860. Min Act: -0.1700

Data Index: 7917470 (Open Web Text)

Max Activating Token Index: 540