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

Dataset: Open Web Text

Neuron 948 in Layer 1

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: 1.4969. Min Range: -1.4969

Max Act: 1.4965. Min Act: -0.1700

Data Index: 2117590 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4969. Min Act: -0.1700

Data Index: 519883 (Open Web Text)

Max Activating Token Index: 902

Text #2

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4585. Min Act: -0.1700

Data Index: 3468081 (Open Web Text)

Max Activating Token Index: 673

Text #3

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4683. Min Act: -0.1700

Data Index: 8283180 (Open Web Text)

Max Activating Token Index: 287

Text #4

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4601. Min Act: -0.1700

Data Index: 7044587 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4434. Min Act: -0.1700

Data Index: 1786445 (Open Web Text)

Max Activating Token Index: 616

Text #6

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4437. Min Act: -0.1699

Data Index: 8067464 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4356. Min Act: -0.1700

Data Index: 976429 (Open Web Text)

Max Activating Token Index: 937

Text #8

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4391. Min Act: -0.1700

Data Index: 7448984 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4434. Min Act: -0.1700

Data Index: 5557914 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4458. Min Act: -0.1700

Data Index: 4321561 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4386. Min Act: -0.1700

Data Index: 7939519 (Open Web Text)

Max Activating Token Index: 358

Text #12

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4204. Min Act: -0.1700

Data Index: 3511013 (Open Web Text)

Max Activating Token Index: 988

Text #13

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4336. Min Act: -0.1700

Data Index: 1677131 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4292. Min Act: -0.1700

Data Index: 1103498 (Open Web Text)

Max Activating Token Index: 695

Text #15

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4290. Min Act: -0.1699

Data Index: 1885710 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4243. Min Act: -0.1700

Data Index: 4513922 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4306. Min Act: -0.1700

Data Index: 6547046 (Open Web Text)

Max Activating Token Index: 398

Text #18

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4218. Min Act: -0.1700

Data Index: 6331504 (Open Web Text)

Max Activating Token Index: 480

Text #19

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4174. Min Act: -0.1699

Data Index: 2117592 (Open Web Text)

Max Activating Token Index: 198