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

Dataset: Open Web Text

Neuron 2759 in Layer 6

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: 3.0954. Min Range: -3.0954

Max Act: 3.0954. Min Act: -0.1700

Data Index: 6870842 (Open Web Text)

Max Activating Token Index: 851

Text #1

Max Range: 3.0954. Min Range: -3.0954

Max Act: 3.0306. Min Act: -0.1700

Data Index: 8316455 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.9822. Min Act: -0.1700

Data Index: 7619274 (Open Web Text)

Max Activating Token Index: 1017

Text #3

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.9189. Min Act: -0.1700

Data Index: 4032854 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.8968. Min Act: -0.1700

Data Index: 5389883 (Open Web Text)

Max Activating Token Index: 774

Text #5

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.9184. Min Act: -0.1700

Data Index: 3598182 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.8814. Min Act: -0.1700

Data Index: 5662073 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.8644. Min Act: -0.1700

Data Index: 1189826 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.8442. Min Act: -0.1700

Data Index: 6358518 (Open Web Text)

Max Activating Token Index: 858

Text #9

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7962. Min Act: -0.1700

Data Index: 4449485 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7831. Min Act: -0.1700

Data Index: 736983 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7791. Min Act: -0.1700

Data Index: 3067140 (Open Web Text)

Max Activating Token Index: 592

Text #12

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7901. Min Act: -0.1700

Data Index: 3638887 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7495. Min Act: -0.1700

Data Index: 8720743 (Open Web Text)

Max Activating Token Index: 145

Text #14

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7612. Min Act: -0.1700

Data Index: 8222853 (Open Web Text)

Max Activating Token Index: 979

Text #15

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7470. Min Act: -0.1700

Data Index: 7619762 (Open Web Text)

Max Activating Token Index: 870

Text #16

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7255. Min Act: -0.1700

Data Index: 8025608 (Open Web Text)

Max Activating Token Index: 834

Text #17

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7136. Min Act: -0.1700

Data Index: 3952439 (Open Web Text)

Max Activating Token Index: 535

Text #18

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7249. Min Act: -0.1700

Data Index: 2378106 (Open Web Text)

Max Activating Token Index: 886

Text #19

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.7321. Min Act: -0.1700

Data Index: 3501527 (Open Web Text)

Max Activating Token Index: 659