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

Dataset: Open Web Text

Neuron 2027 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: 1.3557. Min Range: -1.3557

Max Act: 1.3557. Min Act: -0.0966

Data Index: 6230303 (Open Web Text)

Max Activating Token Index: 895

Text #1

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3432. Min Act: -0.1102

Data Index: 4272102 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3343. Min Act: -0.0901

Data Index: 7710693 (Open Web Text)

Max Activating Token Index: 930

Text #3

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3317. Min Act: -0.1101

Data Index: 7897758 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3331. Min Act: -0.1044

Data Index: 8167537 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3339. Min Act: -0.0784

Data Index: 2537817 (Open Web Text)

Max Activating Token Index: 339

Text #6

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3326. Min Act: -0.0854

Data Index: 7265033 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3281. Min Act: -0.0784

Data Index: 7945990 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3234. Min Act: -0.0784

Data Index: 7972180 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3234. Min Act: -0.0784

Data Index: 4135626 (Open Web Text)

Max Activating Token Index: 156

Text #10

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3131. Min Act: -0.1008

Data Index: 5101436 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3134. Min Act: -0.1174

Data Index: 3850413 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3136. Min Act: -0.0790

Data Index: 2067597 (Open Web Text)

Max Activating Token Index: 364

Text #13

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3064. Min Act: -0.1050

Data Index: 4154064 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3122. Min Act: -0.1277

Data Index: 3832572 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3135. Min Act: -0.0912

Data Index: 4253129 (Open Web Text)

Max Activating Token Index: 655

Text #16

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3103. Min Act: -0.0944

Data Index: 3357001 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3050. Min Act: -0.1647

Data Index: 2281460 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3096. Min Act: -0.0784

Data Index: 3705723 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.3128. Min Act: -0.1160

Data Index: 4979047 (Open Web Text)

Max Activating Token Index: 795