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

Dataset: Open Web Text

Neuron 2161 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: 3.1866. Min Range: -3.1866

Max Act: 3.1866. Min Act: -0.1700

Data Index: 1550763 (Open Web Text)

Max Activating Token Index: 878

Text #1

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.1468. Min Act: -0.1700

Data Index: 3526812 (Open Web Text)

Max Activating Token Index: 114

Text #2

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.1252. Min Act: -0.1700

Data Index: 4712785 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0768. Min Act: -0.1700

Data Index: 6048010 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0707. Min Act: -0.1700

Data Index: 6836552 (Open Web Text)

Max Activating Token Index: 60

Text #5

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0652. Min Act: -0.1700

Data Index: 5763757 (Open Web Text)

Max Activating Token Index: 937

Text #6

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0726. Min Act: -0.1700

Data Index: 4127287 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0512. Min Act: -0.1700

Data Index: 4696522 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0237. Min Act: -0.1700

Data Index: 2607085 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0227. Min Act: -0.1700

Data Index: 4125881 (Open Web Text)

Max Activating Token Index: 829

Text #10

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0307. Min Act: -0.1700

Data Index: 3676522 (Open Web Text)

Max Activating Token Index: 384

Text #11

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0262. Min Act: -0.1700

Data Index: 6048009 (Open Web Text)

Max Activating Token Index: 594

Text #12

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0164. Min Act: -0.1700

Data Index: 3649099 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0103. Min Act: -0.1700

Data Index: 7258897 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0276. Min Act: -0.1700

Data Index: 60361 (Open Web Text)

Max Activating Token Index: 282

Text #15

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0148. Min Act: -0.1700

Data Index: 4279464 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0172. Min Act: -0.1700

Data Index: 4354321 (Open Web Text)

Max Activating Token Index: 949

Text #17

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0094. Min Act: -0.1700

Data Index: 3156563 (Open Web Text)

Max Activating Token Index: 691

Text #18

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9984. Min Act: -0.1700

Data Index: 201010 (Open Web Text)

Max Activating Token Index: 755

Text #19

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9730. Min Act: -0.1700

Data Index: 736312 (Open Web Text)

Max Activating Token Index: 24