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

Dataset: Open Web Text

Neuron 2540 in Layer 6

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: 3.6663. Min Range: -3.6663

Max Act: 3.6663. Min Act: -0.1700

Data Index: 8772529 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.6100. Min Act: -0.1700

Data Index: 3748345 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5481. Min Act: -0.1700

Data Index: 3740662 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5616. Min Act: -0.1700

Data Index: 5879967 (Open Web Text)

Max Activating Token Index: 1012

Text #4

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5382. Min Act: -0.1700

Data Index: 8767621 (Open Web Text)

Max Activating Token Index: 866

Text #5

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.5060. Min Act: -0.1700

Data Index: 2002515 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4784. Min Act: -0.1700

Data Index: 1989169 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4695. Min Act: -0.1700

Data Index: 6745982 (Open Web Text)

Max Activating Token Index: 958

Text #8

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4284. Min Act: -0.1700

Data Index: 6266322 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4356. Min Act: -0.1700

Data Index: 657998 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4136. Min Act: -0.1700

Data Index: 56215 (Open Web Text)

Max Activating Token Index: 430

Text #11

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4286. Min Act: -0.1700

Data Index: 6695246 (Open Web Text)

Max Activating Token Index: 99

Text #12

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4108. Min Act: -0.1700

Data Index: 1250910 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4095. Min Act: -0.1700

Data Index: 4360519 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.3855. Min Act: -0.1700

Data Index: 4572057 (Open Web Text)

Max Activating Token Index: 342

Text #15

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.3957. Min Act: -0.1700

Data Index: 8284926 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.3786. Min Act: -0.1700

Data Index: 6708038 (Open Web Text)

Max Activating Token Index: 799

Text #17

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.3776. Min Act: -0.1700

Data Index: 7862576 (Open Web Text)

Max Activating Token Index: 331

Text #18

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4028. Min Act: -0.1700

Data Index: 6777147 (Open Web Text)

Max Activating Token Index: 999

Text #19

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.3661. Min Act: -0.1700

Data Index: 1907689 (Open Web Text)

Max Activating Token Index: 360