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

Dataset: Open Web Text

Neuron 182 in Layer 4

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: 3.2458. Min Range: -3.2458

Max Act: 3.2458. Min Act: -0.1700

Data Index: 7475111 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.2215. Min Act: -0.1700

Data Index: 1913702 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1980. Min Act: -0.1700

Data Index: 947945 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.2095. Min Act: -0.1700

Data Index: 1841657 (Open Web Text)

Max Activating Token Index: 460

Text #4

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1645. Min Act: -0.1700

Data Index: 6754276 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1795. Min Act: -0.1700

Data Index: 7759666 (Open Web Text)

Max Activating Token Index: 565

Text #6

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1945. Min Act: -0.1700

Data Index: 4095664 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1479. Min Act: -0.1700

Data Index: 2519119 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1371. Min Act: -0.1700

Data Index: 1496232 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1444. Min Act: -0.1700

Data Index: 2432102 (Open Web Text)

Max Activating Token Index: 169

Text #10

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1372. Min Act: -0.1700

Data Index: 5802159 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1294. Min Act: -0.1700

Data Index: 3119797 (Open Web Text)

Max Activating Token Index: 955

Text #12

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1508. Min Act: -0.1700

Data Index: 4330888 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1485. Min Act: -0.1700

Data Index: 3917129 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1362. Min Act: -0.1700

Data Index: 7054604 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1137. Min Act: -0.1700

Data Index: 1048234 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1322. Min Act: -0.1700

Data Index: 7971478 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1395. Min Act: -0.1700

Data Index: 1024346 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1063. Min Act: -0.1700

Data Index: 8318771 (Open Web Text)

Max Activating Token Index: 491

Text #19

Max Range: 3.2458. Min Range: -3.2458

Max Act: 3.1304. Min Act: -0.1700

Data Index: 2111613 (Open Web Text)

Max Activating Token Index: 189