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

Dataset: Open Web Text

Neuron 864 in Layer 0

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: 1.4714. Min Range: -1.4714

Max Act: 1.4668. Min Act: -0.1407

Data Index: 191227 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4714. Min Act: -0.1140

Data Index: 4741929 (Open Web Text)

Max Activating Token Index: 948

Text #2

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4658. Min Act: -0.1332

Data Index: 3273365 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4592. Min Act: -0.1558

Data Index: 121874 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4498. Min Act: -0.1358

Data Index: 7921689 (Open Web Text)

Max Activating Token Index: 818

Text #5

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4473. Min Act: -0.0096

Data Index: 7168384 (Open Web Text)

Max Activating Token Index: 699

Text #6

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4413. Min Act: 0.1508

Data Index: 385312 (Open Web Text)

Max Activating Token Index: 233

Text #7

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4334. Min Act: -0.0840

Data Index: 5925825 (Open Web Text)

Max Activating Token Index: 310

Text #8

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4346. Min Act: -0.0840

Data Index: 1649935 (Open Web Text)

Max Activating Token Index: 833

Text #9

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4284. Min Act: -0.0758

Data Index: 3273356 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4251. Min Act: -0.1287

Data Index: 2074600 (Open Web Text)

Max Activating Token Index: 166

Text #11

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4310. Min Act: -0.1638

Data Index: 6512544 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4323. Min Act: -0.1640

Data Index: 4911571 (Open Web Text)

Max Activating Token Index: 989

Text #13

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4292. Min Act: -0.1106

Data Index: 3705824 (Open Web Text)

Max Activating Token Index: 1003

Text #14

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4188. Min Act: -0.1630

Data Index: 970176 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4209. Min Act: -0.0714

Data Index: 3705165 (Open Web Text)

Max Activating Token Index: 155

Text #16

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4143. Min Act: -0.1165

Data Index: 3571407 (Open Web Text)

Max Activating Token Index: 322

Text #17

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4155. Min Act: -0.0846

Data Index: 1579811 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4136. Min Act: -0.1210

Data Index: 6164997 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4141. Min Act: -0.1347

Data Index: 2249489 (Open Web Text)

Max Activating Token Index: 197