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

Dataset: Open Web Text

Neuron 2817 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: 6.1818. Min Range: -6.1818

Max Act: 6.1818. Min Act: -0.1700

Data Index: 4344661 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 6.1818. Min Range: -6.1818

Max Act: 6.1118. Min Act: -0.1700

Data Index: 7353521 (Open Web Text)

Max Activating Token Index: 138

Text #2

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.9899. Min Act: -0.1700

Data Index: 5529810 (Open Web Text)

Max Activating Token Index: 872

Text #3

Max Range: 6.1818. Min Range: -6.1818

Max Act: 6.1055. Min Act: -0.1700

Data Index: 6031718 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.9663. Min Act: -0.1700

Data Index: 4236539 (Open Web Text)

Max Activating Token Index: 199

Text #5

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.9303. Min Act: -0.1700

Data Index: 4010211 (Open Web Text)

Max Activating Token Index: 809

Text #6

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.9211. Min Act: -0.1700

Data Index: 6146094 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.9790. Min Act: -0.1700

Data Index: 8670071 (Open Web Text)

Max Activating Token Index: 779

Text #8

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8256. Min Act: -0.1700

Data Index: 2229984 (Open Web Text)

Max Activating Token Index: 890

Text #9

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8612. Min Act: -0.1700

Data Index: 8425991 (Open Web Text)

Max Activating Token Index: 112

Text #10

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8738. Min Act: -0.1700

Data Index: 699298 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8453. Min Act: -0.1700

Data Index: 6343045 (Open Web Text)

Max Activating Token Index: 353

Text #12

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8369. Min Act: -0.1700

Data Index: 4405711 (Open Web Text)

Max Activating Token Index: 33

Text #13

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8722. Min Act: -0.1700

Data Index: 3518376 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8226. Min Act: -0.1700

Data Index: 8375681 (Open Web Text)

Max Activating Token Index: 162

Text #15

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8913. Min Act: -0.1700

Data Index: 2113448 (Open Web Text)

Max Activating Token Index: 317

Text #16

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.8133. Min Act: -0.1700

Data Index: 5873988 (Open Web Text)

Max Activating Token Index: 626

Text #17

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.7438. Min Act: -0.1700

Data Index: 4236526 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.7044. Min Act: -0.1700

Data Index: 3622285 (Open Web Text)

Max Activating Token Index: 332

Text #19

Max Range: 6.1818. Min Range: -6.1818

Max Act: 5.7169. Min Act: -0.1700

Data Index: 6085310 (Open Web Text)

Max Activating Token Index: 272