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

Dataset: Open Web Text

Neuron 2913 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: 3.0460. Min Range: -3.0460

Max Act: 3.0460. Min Act: -0.1700

Data Index: 6060435 (Open Web Text)

Max Activating Token Index: 267

Text #1

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.9297. Min Act: -0.1700

Data Index: 2062551 (Open Web Text)

Max Activating Token Index: 464

Text #2

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8828. Min Act: -0.1700

Data Index: 1551951 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8693. Min Act: -0.1700

Data Index: 97435 (Open Web Text)

Max Activating Token Index: 569

Text #4

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8846. Min Act: -0.1700

Data Index: 1209928 (Open Web Text)

Max Activating Token Index: 331

Text #5

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8526. Min Act: -0.1700

Data Index: 1040125 (Open Web Text)

Max Activating Token Index: 199

Text #6

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8544. Min Act: -0.1700

Data Index: 5103357 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8646. Min Act: -0.1700

Data Index: 3609240 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8332. Min Act: -0.1700

Data Index: 5081679 (Open Web Text)

Max Activating Token Index: 648

Text #9

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8179. Min Act: -0.1700

Data Index: 5138026 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8268. Min Act: -0.1700

Data Index: 7078496 (Open Web Text)

Max Activating Token Index: 693

Text #11

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8501. Min Act: -0.1700

Data Index: 4498704 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8024. Min Act: -0.1700

Data Index: 1930355 (Open Web Text)

Max Activating Token Index: 111

Text #13

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8029. Min Act: -0.1700

Data Index: 4377743 (Open Web Text)

Max Activating Token Index: 224

Text #14

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.7978. Min Act: -0.1700

Data Index: 5393411 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.7966. Min Act: -0.1700

Data Index: 2028426 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.7987. Min Act: -0.1700

Data Index: 4237102 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8048. Min Act: -0.1700

Data Index: 6414627 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.8146. Min Act: -0.1700

Data Index: 2125371 (Open Web Text)

Max Activating Token Index: 275

Text #19

Max Range: 3.0460. Min Range: -3.0460

Max Act: 2.7831. Min Act: -0.1700

Data Index: 2719015 (Open Web Text)

Max Activating Token Index: 513