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

Dataset: Open Web Text

Neuron 2130 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: 1.4261. Min Range: -1.4261

Max Act: 1.4261. Min Act: -0.1700

Data Index: 702513 (Open Web Text)

Max Activating Token Index: 252

Text #1

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.4149. Min Act: -0.1700

Data Index: 5508243 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3824. Min Act: -0.1697

Data Index: 840716 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3712. Min Act: -0.1662

Data Index: 4332531 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3641. Min Act: -0.1693

Data Index: 4637867 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3707. Min Act: -0.1692

Data Index: 4637864 (Open Web Text)

Max Activating Token Index: 320

Text #6

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3673. Min Act: -0.1698

Data Index: 8026317 (Open Web Text)

Max Activating Token Index: 655

Text #7

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3663. Min Act: -0.1699

Data Index: 6338759 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3608. Min Act: -0.1700

Data Index: 7511604 (Open Web Text)

Max Activating Token Index: 703

Text #9

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3654. Min Act: -0.1646

Data Index: 8492994 (Open Web Text)

Max Activating Token Index: 789

Text #10

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3577. Min Act: -0.1700

Data Index: 5932689 (Open Web Text)

Max Activating Token Index: 955

Text #11

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3636. Min Act: -0.1700

Data Index: 3546036 (Open Web Text)

Max Activating Token Index: 571

Text #12

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3466. Min Act: -0.1700

Data Index: 8667153 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3447. Min Act: -0.1700

Data Index: 1004183 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3538. Min Act: -0.1699

Data Index: 6453892 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3462. Min Act: -0.1700

Data Index: 6981367 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3434. Min Act: -0.1700

Data Index: 2807933 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3461. Min Act: -0.1695

Data Index: 2686916 (Open Web Text)

Max Activating Token Index: 950

Text #18

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3464. Min Act: -0.1700

Data Index: 7422427 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3475. Min Act: -0.1700

Data Index: 2699191 (Open Web Text)

Max Activating Token Index: 995