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

Dataset: Open Web Text

Neuron 1495 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: 1.8045. Min Range: -1.8045

Max Act: 1.8045. Min Act: -0.1681

Data Index: 2926836 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.7585. Min Act: -0.1700

Data Index: 7011648 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.7501. Min Act: -0.1698

Data Index: 6146181 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.7393. Min Act: -0.1700

Data Index: 886521 (Open Web Text)

Max Activating Token Index: 94

Text #4

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6900. Min Act: -0.1699

Data Index: 2509964 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6784. Min Act: -0.1700

Data Index: 2097206 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6768. Min Act: -0.1700

Data Index: 4106246 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6590. Min Act: -0.1700

Data Index: 8434502 (Open Web Text)

Max Activating Token Index: 310

Text #8

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6533. Min Act: -0.1700

Data Index: 3486852 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6492. Min Act: -0.1699

Data Index: 4350396 (Open Web Text)

Max Activating Token Index: 876

Text #10

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6548. Min Act: -0.1700

Data Index: 5785567 (Open Web Text)

Max Activating Token Index: 268

Text #11

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6463. Min Act: -0.1696

Data Index: 1743037 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6366. Min Act: -0.1700

Data Index: 960467 (Open Web Text)

Max Activating Token Index: 428

Text #13

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6447. Min Act: -0.1698

Data Index: 8113795 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6401. Min Act: -0.1697

Data Index: 5682123 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6387. Min Act: -0.1693

Data Index: 2463083 (Open Web Text)

Max Activating Token Index: 253

Text #16

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6365. Min Act: -0.1700

Data Index: 6808304 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6468. Min Act: -0.1700

Data Index: 4542847 (Open Web Text)

Max Activating Token Index: 61

Text #18

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6312. Min Act: -0.1695

Data Index: 7214126 (Open Web Text)

Max Activating Token Index: 569

Text #19

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6298. Min Act: -0.1690

Data Index: 7488983 (Open Web Text)

Max Activating Token Index: 262