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

Dataset: Open Web Text

Neuron 3067 in Layer 1

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: 1.7729. Min Range: -1.7729

Max Act: 1.7729. Min Act: -0.1700

Data Index: 7316225 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7523. Min Act: -0.1700

Data Index: 8026634 (Open Web Text)

Max Activating Token Index: 189

Text #2

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7501. Min Act: -0.1700

Data Index: 4303235 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7200. Min Act: -0.1700

Data Index: 377432 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7192. Min Act: -0.1700

Data Index: 1618220 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7091. Min Act: -0.1700

Data Index: 410316 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7103. Min Act: -0.1700

Data Index: 1203552 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.7156. Min Act: -0.1700

Data Index: 310515 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6956. Min Act: -0.1700

Data Index: 2231664 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6996. Min Act: -0.1700

Data Index: 580502 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6967. Min Act: -0.1700

Data Index: 5400425 (Open Web Text)

Max Activating Token Index: 248

Text #11

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6939. Min Act: -0.1700

Data Index: 1453278 (Open Web Text)

Max Activating Token Index: 1021

Text #12

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6910. Min Act: -0.1700

Data Index: 5018507 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6915. Min Act: -0.1700

Data Index: 7376357 (Open Web Text)

Max Activating Token Index: 723

Text #14

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6798. Min Act: -0.1700

Data Index: 7472282 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6859. Min Act: -0.1700

Data Index: 8748621 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6879. Min Act: -0.1700

Data Index: 461222 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6801. Min Act: -0.1700

Data Index: 4452021 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6675. Min Act: -0.1700

Data Index: 6796307 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 1.7729. Min Range: -1.7729

Max Act: 1.6768. Min Act: -0.1700

Data Index: 3390008 (Open Web Text)

Max Activating Token Index: 736