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

Dataset: Open Web Text

Neuron 194 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: 3.3711. Min Range: -3.3711

Max Act: 3.3711. Min Act: -0.1700

Data Index: 7016445 (Open Web Text)

Max Activating Token Index: 801

Text #1

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.3443. Min Act: -0.1700

Data Index: 4724929 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.3177. Min Act: -0.1700

Data Index: 1963871 (Open Web Text)

Max Activating Token Index: 624

Text #3

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.3105. Min Act: -0.1700

Data Index: 3171118 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2999. Min Act: -0.1700

Data Index: 8191836 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2951. Min Act: -0.1700

Data Index: 8751794 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2874. Min Act: -0.1700

Data Index: 651421 (Open Web Text)

Max Activating Token Index: 824

Text #7

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2850. Min Act: -0.1700

Data Index: 1210299 (Open Web Text)

Max Activating Token Index: 639

Text #8

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2962. Min Act: -0.1700

Data Index: 3739323 (Open Web Text)

Max Activating Token Index: 898

Text #9

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2670. Min Act: -0.1700

Data Index: 212152 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2706. Min Act: -0.1700

Data Index: 5118640 (Open Web Text)

Max Activating Token Index: 421

Text #11

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2669. Min Act: -0.1700

Data Index: 6036770 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2627. Min Act: -0.1700

Data Index: 2505088 (Open Web Text)

Max Activating Token Index: 952

Text #13

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1388117 (Open Web Text)

Max Activating Token Index: 137

Text #14

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2694. Min Act: -0.1700

Data Index: 1751041 (Open Web Text)

Max Activating Token Index: 710

Text #15

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2409. Min Act: -0.1700

Data Index: 7592975 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2442. Min Act: -0.1700

Data Index: 4067768 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2213. Min Act: -0.1700

Data Index: 7113126 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2521. Min Act: -0.1700

Data Index: 6696367 (Open Web Text)

Max Activating Token Index: 166

Text #19

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2268. Min Act: -0.1700

Data Index: 3389721 (Open Web Text)

Max Activating Token Index: 788