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

Dataset: Open Web Text

Neuron 584 in Layer 2

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: 3.4513. Min Range: -3.4513

Max Act: 3.4513. Min Act: -0.1700

Data Index: 7897557 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3869. Min Act: -0.1700

Data Index: 5311232 (Open Web Text)

Max Activating Token Index: 342

Text #2

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3890. Min Act: -0.1700

Data Index: 3805352 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3956. Min Act: -0.1700

Data Index: 2340969 (Open Web Text)

Max Activating Token Index: 76

Text #4

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3898. Min Act: -0.1700

Data Index: 825921 (Open Web Text)

Max Activating Token Index: 824

Text #5

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3986. Min Act: -0.1700

Data Index: 7692437 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3728. Min Act: -0.1700

Data Index: 3925165 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3560. Min Act: -0.1700

Data Index: 6775521 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3390. Min Act: -0.1700

Data Index: 5258042 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.2999. Min Act: -0.1700

Data Index: 7756241 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3239. Min Act: -0.1700

Data Index: 987960 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3319. Min Act: -0.1700

Data Index: 7636801 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3222. Min Act: -0.1700

Data Index: 7064901 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3470. Min Act: -0.1700

Data Index: 228557 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3264. Min Act: -0.1700

Data Index: 3922243 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3240. Min Act: -0.1700

Data Index: 2999851 (Open Web Text)

Max Activating Token Index: 357

Text #16

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3222. Min Act: -0.1700

Data Index: 950870 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3052. Min Act: -0.1700

Data Index: 5350655 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3287. Min Act: -0.1700

Data Index: 3805353 (Open Web Text)

Max Activating Token Index: 175

Text #19

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3301. Min Act: -0.1700

Data Index: 6857802 (Open Web Text)

Max Activating Token Index: 289