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

Dataset: Open Web Text

Neuron 2623 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: 2.1974. Min Range: -2.1974

Max Act: 2.1974. Min Act: -0.1700

Data Index: 370784 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1869. Min Act: -0.1700

Data Index: 2297449 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1527. Min Act: -0.1700

Data Index: 7804709 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1561. Min Act: -0.1700

Data Index: 3711195 (Open Web Text)

Max Activating Token Index: 554

Text #4

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1307. Min Act: -0.1700

Data Index: 5876688 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1286. Min Act: -0.1700

Data Index: 6201630 (Open Web Text)

Max Activating Token Index: 628

Text #6

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1300. Min Act: -0.1700

Data Index: 8788266 (Open Web Text)

Max Activating Token Index: 722

Text #7

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1258. Min Act: -0.1700

Data Index: 1857955 (Open Web Text)

Max Activating Token Index: 546

Text #8

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1274. Min Act: -0.1700

Data Index: 6179311 (Open Web Text)

Max Activating Token Index: 732

Text #9

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1166. Min Act: -0.1700

Data Index: 79886 (Open Web Text)

Max Activating Token Index: 838

Text #10

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1113. Min Act: -0.1700

Data Index: 6400256 (Open Web Text)

Max Activating Token Index: 481

Text #11

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1179. Min Act: -0.1700

Data Index: 6363658 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1211. Min Act: -0.1700

Data Index: 8499687 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.0841. Min Act: -0.1700

Data Index: 1342709 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1210. Min Act: -0.1700

Data Index: 78460 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.0920. Min Act: -0.1700

Data Index: 1185138 (Open Web Text)

Max Activating Token Index: 568

Text #16

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.1070. Min Act: -0.1700

Data Index: 7945636 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.0958. Min Act: -0.1700

Data Index: 6413140 (Open Web Text)

Max Activating Token Index: 358

Text #18

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.0937. Min Act: -0.1700

Data Index: 812211 (Open Web Text)

Max Activating Token Index: 886

Text #19

Max Range: 2.1974. Min Range: -2.1974

Max Act: 2.0968. Min Act: -0.1700

Data Index: 764636 (Open Web Text)

Max Activating Token Index: 869