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

Dataset: Open Web Text

Neuron 2850 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: 3.4280. Min Range: -3.4280

Max Act: 3.4280. Min Act: -0.1700

Data Index: 3318436 (Open Web Text)

Max Activating Token Index: 323

Text #1

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3162. Min Act: -0.1700

Data Index: 1771129 (Open Web Text)

Max Activating Token Index: 88

Text #2

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3249. Min Act: -0.1700

Data Index: 3373866 (Open Web Text)

Max Activating Token Index: 204

Text #3

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.3195. Min Act: -0.1700

Data Index: 8181218 (Open Web Text)

Max Activating Token Index: 457

Text #4

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2977. Min Act: -0.1700

Data Index: 9134 (Open Web Text)

Max Activating Token Index: 128

Text #5

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2585. Min Act: -0.1700

Data Index: 2509123 (Open Web Text)

Max Activating Token Index: 138

Text #6

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2339. Min Act: -0.1700

Data Index: 5622380 (Open Web Text)

Max Activating Token Index: 748

Text #7

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2473. Min Act: -0.1700

Data Index: 1166082 (Open Web Text)

Max Activating Token Index: 440

Text #8

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.2283. Min Act: -0.1700

Data Index: 1626934 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1513. Min Act: -0.1700

Data Index: 6269592 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1675. Min Act: -0.1700

Data Index: 2277185 (Open Web Text)

Max Activating Token Index: 419

Text #11

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1427. Min Act: -0.1700

Data Index: 7450193 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1678. Min Act: -0.1700

Data Index: 1610354 (Open Web Text)

Max Activating Token Index: 223

Text #13

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1468. Min Act: -0.1700

Data Index: 7363967 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1400. Min Act: -0.1700

Data Index: 1362540 (Open Web Text)

Max Activating Token Index: 588

Text #15

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1363. Min Act: -0.1700

Data Index: 1769517 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1084. Min Act: -0.1700

Data Index: 3256195 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1007. Min Act: -0.1700

Data Index: 4246836 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.1070. Min Act: -0.1700

Data Index: 1344230 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 3.4280. Min Range: -3.4280

Max Act: 3.0899. Min Act: -0.1700

Data Index: 6285476 (Open Web Text)

Max Activating Token Index: 257