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

Dataset: Open Web Text

Neuron 391 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: 3.3402. Min Range: -3.3402

Max Act: 3.3402. Min Act: -0.1700

Data Index: 765806 (Open Web Text)

Max Activating Token Index: 353

Text #1

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.2830. Min Act: -0.1700

Data Index: 3721746 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.2533. Min Act: -0.1700

Data Index: 321568 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.2608. Min Act: -0.1700

Data Index: 4711748 (Open Web Text)

Max Activating Token Index: 634

Text #4

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.2119. Min Act: -0.1700

Data Index: 6668935 (Open Web Text)

Max Activating Token Index: 168

Text #5

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1817. Min Act: -0.1700

Data Index: 8474807 (Open Web Text)

Max Activating Token Index: 731

Text #6

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1763. Min Act: -0.1700

Data Index: 401895 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1574. Min Act: -0.1700

Data Index: 5374501 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1385. Min Act: -0.1700

Data Index: 1644510 (Open Web Text)

Max Activating Token Index: 252

Text #9

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1546. Min Act: -0.1700

Data Index: 7302819 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1347. Min Act: -0.1700

Data Index: 5379005 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1350. Min Act: -0.1700

Data Index: 110022 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1455. Min Act: -0.1700

Data Index: 6551934 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1563. Min Act: -0.1700

Data Index: 8417458 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1191. Min Act: -0.1700

Data Index: 7334117 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1147. Min Act: -0.1700

Data Index: 4329149 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1438. Min Act: -0.1700

Data Index: 852644 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1091. Min Act: -0.1700

Data Index: 8089708 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1228. Min Act: -0.1700

Data Index: 8070274 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 3.3402. Min Range: -3.3402

Max Act: 3.1101. Min Act: -0.1700

Data Index: 7543113 (Open Web Text)

Max Activating Token Index: 1010