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

Dataset: Open Web Text

Neuron 2782 in Layer 3

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: 3.4315. Min Range: -3.4315

Max Act: 3.4315. Min Act: -0.1700

Data Index: 5878546 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3851. Min Act: -0.1700

Data Index: 3350836 (Open Web Text)

Max Activating Token Index: 331

Text #2

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3193. Min Act: -0.1700

Data Index: 821702 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3836. Min Act: -0.1700

Data Index: 3533702 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3216. Min Act: -0.1700

Data Index: 7742434 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2846. Min Act: -0.1700

Data Index: 4823471 (Open Web Text)

Max Activating Token Index: 368

Text #6

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2860. Min Act: -0.1700

Data Index: 4924324 (Open Web Text)

Max Activating Token Index: 198

Text #7

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2910. Min Act: -0.1700

Data Index: 3309709 (Open Web Text)

Max Activating Token Index: 399

Text #8

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2922. Min Act: -0.1700

Data Index: 6620474 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2567. Min Act: -0.1700

Data Index: 2162956 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3265. Min Act: -0.1700

Data Index: 1462116 (Open Web Text)

Max Activating Token Index: 253

Text #11

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2452. Min Act: -0.1700

Data Index: 3263069 (Open Web Text)

Max Activating Token Index: 164

Text #12

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2977. Min Act: -0.1700

Data Index: 3384777 (Open Web Text)

Max Activating Token Index: 837

Text #13

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2218. Min Act: -0.1700

Data Index: 1407362 (Open Web Text)

Max Activating Token Index: 737

Text #14

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3048. Min Act: -0.1700

Data Index: 3772001 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2497. Min Act: -0.1700

Data Index: 3188093 (Open Web Text)

Max Activating Token Index: 392

Text #16

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2559. Min Act: -0.1700

Data Index: 2927251 (Open Web Text)

Max Activating Token Index: 146

Text #17

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2473. Min Act: -0.1700

Data Index: 1391983 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3117. Min Act: -0.1700

Data Index: 6525037 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2636. Min Act: -0.1700

Data Index: 1162230 (Open Web Text)

Max Activating Token Index: 860