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

Dataset: Open Web Text

Neuron 684 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: 3.4427. Min Range: -3.4427

Max Act: 3.4427. Min Act: -0.1700

Data Index: 4965069 (Open Web Text)

Max Activating Token Index: 886

Text #1

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.3962. Min Act: -0.1700

Data Index: 5243396 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.3526. Min Act: -0.1700

Data Index: 3812790 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.3589. Min Act: -0.1700

Data Index: 1727001 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.3021. Min Act: -0.1700

Data Index: 4169897 (Open Web Text)

Max Activating Token Index: 526

Text #5

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2866. Min Act: -0.1700

Data Index: 1767662 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.3190. Min Act: -0.1700

Data Index: 41547 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2746. Min Act: -0.1700

Data Index: 2958271 (Open Web Text)

Max Activating Token Index: 499

Text #8

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2919. Min Act: -0.1700

Data Index: 8506587 (Open Web Text)

Max Activating Token Index: 969

Text #9

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2737. Min Act: -0.1700

Data Index: 4091736 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2470. Min Act: -0.1700

Data Index: 1807129 (Open Web Text)

Max Activating Token Index: 683

Text #11

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2588. Min Act: -0.1700

Data Index: 8023003 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2392. Min Act: -0.1700

Data Index: 6289939 (Open Web Text)

Max Activating Token Index: 650

Text #13

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2314. Min Act: -0.1700

Data Index: 53261 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2442. Min Act: -0.1700

Data Index: 2923178 (Open Web Text)

Max Activating Token Index: 654

Text #15

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.1971. Min Act: -0.1700

Data Index: 277851 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2358. Min Act: -0.1700

Data Index: 772566 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.2286. Min Act: -0.1700

Data Index: 20635 (Open Web Text)

Max Activating Token Index: 836

Text #18

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.1617. Min Act: -0.1700

Data Index: 4819775 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 3.4427. Min Range: -3.4427

Max Act: 3.1752. Min Act: -0.1700

Data Index: 8601872 (Open Web Text)

Max Activating Token Index: 872