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

Dataset: Open Web Text

Neuron 1604 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: 3.4586. Min Range: -3.4586

Max Act: 3.4586. Min Act: -0.1700

Data Index: 7283585 (Open Web Text)

Max Activating Token Index: 865

Text #1

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.3865. Min Act: -0.1700

Data Index: 1703631 (Open Web Text)

Max Activating Token Index: 149

Text #2

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2796. Min Act: -0.1700

Data Index: 6928740 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2744. Min Act: -0.1700

Data Index: 365764 (Open Web Text)

Max Activating Token Index: 939

Text #4

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2498. Min Act: -0.1700

Data Index: 3910050 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2795. Min Act: -0.1700

Data Index: 4491360 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2892. Min Act: -0.1700

Data Index: 2295762 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2609. Min Act: -0.1700

Data Index: 5924737 (Open Web Text)

Max Activating Token Index: 313

Text #8

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2537. Min Act: -0.1700

Data Index: 990406 (Open Web Text)

Max Activating Token Index: 110

Text #9

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2462. Min Act: -0.1700

Data Index: 4145505 (Open Web Text)

Max Activating Token Index: 936

Text #10

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2217. Min Act: -0.1700

Data Index: 5121260 (Open Web Text)

Max Activating Token Index: 721

Text #11

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2087. Min Act: -0.1700

Data Index: 2418661 (Open Web Text)

Max Activating Token Index: 698

Text #12

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2243. Min Act: -0.1700

Data Index: 5316980 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2321. Min Act: -0.1700

Data Index: 4907695 (Open Web Text)

Max Activating Token Index: 428

Text #14

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2141. Min Act: -0.1700

Data Index: 2869733 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.2017. Min Act: -0.1700

Data Index: 5946196 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.1974. Min Act: -0.1700

Data Index: 8446680 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.1926. Min Act: -0.1700

Data Index: 762160 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.1894. Min Act: -0.1700

Data Index: 3289164 (Open Web Text)

Max Activating Token Index: 433

Text #19

Max Range: 3.4586. Min Range: -3.4586

Max Act: 3.1766. Min Act: -0.1700

Data Index: 7179695 (Open Web Text)

Max Activating Token Index: 240