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

Dataset: Open Web Text

Neuron 72 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: 4.8413. Min Range: -4.8413

Max Act: 4.8413. Min Act: -0.1700

Data Index: 3116432 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.8143. Min Act: -0.1700

Data Index: 5237927 (Open Web Text)

Max Activating Token Index: 455

Text #2

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.8160. Min Act: -0.1700

Data Index: 3920092 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.7555. Min Act: -0.1700

Data Index: 4881238 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.7285. Min Act: -0.1700

Data Index: 2140872 (Open Web Text)

Max Activating Token Index: 214

Text #5

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.6894. Min Act: -0.1700

Data Index: 4966632 (Open Web Text)

Max Activating Token Index: 746

Text #6

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5884. Min Act: -0.1700

Data Index: 3588173 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.6377. Min Act: -0.1700

Data Index: 7988110 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.6526. Min Act: -0.1700

Data Index: 4242780 (Open Web Text)

Max Activating Token Index: 764

Text #9

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.6324. Min Act: -0.1700

Data Index: 1172090 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.6318. Min Act: -0.1700

Data Index: 3581115 (Open Web Text)

Max Activating Token Index: 556

Text #11

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5962. Min Act: -0.1700

Data Index: 7988111 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.6233. Min Act: -0.1700

Data Index: 166098 (Open Web Text)

Max Activating Token Index: 220

Text #13

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.6076. Min Act: -0.1700

Data Index: 5202025 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5754. Min Act: -0.1700

Data Index: 2955139 (Open Web Text)

Max Activating Token Index: 689

Text #15

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5915. Min Act: -0.1700

Data Index: 1563277 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5756. Min Act: -0.1700

Data Index: 7921360 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5468. Min Act: -0.1700

Data Index: 3406487 (Open Web Text)

Max Activating Token Index: 813

Text #18

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5544. Min Act: -0.1700

Data Index: 5749790 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 4.8413. Min Range: -4.8413

Max Act: 4.5262. Min Act: -0.1700

Data Index: 1844955 (Open Web Text)

Max Activating Token Index: 257