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

Dataset: Open Web Text

Neuron 2856 in Layer 4

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: 5.4674. Min Range: -5.4674

Max Act: 5.4591. Min Act: -0.1700

Data Index: 1785624 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.4674. Min Act: -0.1700

Data Index: 6171821 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.3609. Min Act: -0.1700

Data Index: 530364 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.3033. Min Act: -0.1700

Data Index: 3067036 (Open Web Text)

Max Activating Token Index: 281

Text #4

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.2693. Min Act: -0.1700

Data Index: 4909135 (Open Web Text)

Max Activating Token Index: 395

Text #5

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.3079. Min Act: -0.1699

Data Index: 3030095 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.2527. Min Act: -0.1700

Data Index: 4220196 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.2826. Min Act: -0.1698

Data Index: 7627325 (Open Web Text)

Max Activating Token Index: 442

Text #8

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.3088. Min Act: -0.1700

Data Index: 6171826 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.2279. Min Act: -0.1700

Data Index: 852197 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1336. Min Act: -0.1700

Data Index: 2318986 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1841. Min Act: -0.1700

Data Index: 7471053 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.2721. Min Act: -0.1700

Data Index: 8230033 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1509. Min Act: -0.1700

Data Index: 5097559 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1719. Min Act: -0.1700

Data Index: 2934265 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1661. Min Act: -0.1699

Data Index: 6951243 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1476. Min Act: -0.1700

Data Index: 2011906 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.0619. Min Act: -0.1700

Data Index: 7956875 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1519. Min Act: -0.1700

Data Index: 904460 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 5.4674. Min Range: -5.4674

Max Act: 5.1345. Min Act: -0.1700

Data Index: 1954484 (Open Web Text)

Max Activating Token Index: 1019