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

Dataset: Open Web Text

Neuron 538 in Layer 2

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: 1.2885. Min Range: -1.2885

Max Act: 1.2885. Min Act: -0.1700

Data Index: 5353449 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2813. Min Act: -0.1700

Data Index: 967219 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2734. Min Act: -0.1700

Data Index: 3909225 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2745. Min Act: -0.1694

Data Index: 8010677 (Open Web Text)

Max Activating Token Index: 598

Text #4

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2587. Min Act: -0.1700

Data Index: 7239342 (Open Web Text)

Max Activating Token Index: 201

Text #5

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2489. Min Act: -0.1700

Data Index: 8470003 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2374. Min Act: -0.1700

Data Index: 4112270 (Open Web Text)

Max Activating Token Index: 118

Text #7

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2368. Min Act: -0.1700

Data Index: 8467268 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2419. Min Act: -0.1696

Data Index: 7926949 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2453. Min Act: -0.1699

Data Index: 4924665 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2512. Min Act: -0.1692

Data Index: 8463648 (Open Web Text)

Max Activating Token Index: 169

Text #11

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2433. Min Act: -0.1499

Data Index: 1712393 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2404. Min Act: -0.1700

Data Index: 8150541 (Open Web Text)

Max Activating Token Index: 686

Text #13

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2371. Min Act: -0.1700

Data Index: 7306713 (Open Web Text)

Max Activating Token Index: 326

Text #14

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2375. Min Act: -0.1699

Data Index: 4951349 (Open Web Text)

Max Activating Token Index: 77

Text #15

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2306. Min Act: -0.1700

Data Index: 8055042 (Open Web Text)

Max Activating Token Index: 505

Text #16

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2378. Min Act: -0.1697

Data Index: 7175931 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2361. Min Act: -0.1573

Data Index: 4924666 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2377. Min Act: -0.1700

Data Index: 8010678 (Open Web Text)

Max Activating Token Index: 515

Text #19

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2273. Min Act: -0.1700

Data Index: 4646306 (Open Web Text)

Max Activating Token Index: 953