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

Dataset: Open Web Text

Neuron 1341 in Layer 5

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: 4.5310. Min Range: -4.5310

Max Act: 4.5310. Min Act: -0.1700

Data Index: 3320918 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4072. Min Act: -0.1700

Data Index: 1095692 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.3193. Min Act: -0.1700

Data Index: 7792382 (Open Web Text)

Max Activating Token Index: 824

Text #3

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.1878. Min Act: -0.1700

Data Index: 7243496 (Open Web Text)

Max Activating Token Index: 208

Text #4

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.1942. Min Act: -0.1700

Data Index: 3659425 (Open Web Text)

Max Activating Token Index: 1005

Text #5

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.1040. Min Act: -0.1700

Data Index: 2523237 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0978. Min Act: -0.1700

Data Index: 1754735 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0700. Min Act: -0.1700

Data Index: 4284125 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0794. Min Act: -0.1700

Data Index: 7871644 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0551. Min Act: -0.1700

Data Index: 369686 (Open Web Text)

Max Activating Token Index: 908

Text #10

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0861. Min Act: -0.1700

Data Index: 5784631 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0344. Min Act: -0.1700

Data Index: 4281134 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0190. Min Act: -0.1700

Data Index: 3690306 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 4.5310. Min Range: -4.5310

Max Act: 3.9133. Min Act: -0.1700

Data Index: 5153015 (Open Web Text)

Max Activating Token Index: 802

Text #14

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0065. Min Act: -0.1700

Data Index: 3007700 (Open Web Text)

Max Activating Token Index: 260

Text #15

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.0267. Min Act: -0.1700

Data Index: 821063 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 4.5310. Min Range: -4.5310

Max Act: 3.8950. Min Act: -0.1700

Data Index: 4169565 (Open Web Text)

Max Activating Token Index: 212

Text #17

Max Range: 4.5310. Min Range: -4.5310

Max Act: 3.9202. Min Act: -0.1700

Data Index: 6486995 (Open Web Text)

Max Activating Token Index: 938

Text #18

Max Range: 4.5310. Min Range: -4.5310

Max Act: 3.8536. Min Act: -0.1700

Data Index: 5387788 (Open Web Text)

Max Activating Token Index: 879

Text #19

Max Range: 4.5310. Min Range: -4.5310

Max Act: 3.8890. Min Act: -0.1700

Data Index: 1852163 (Open Web Text)

Max Activating Token Index: 809