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

Dataset: Open Web Text

Neuron 2375 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: 4.4454. Min Range: -4.4454

Max Act: 4.4454. Min Act: -0.1700

Data Index: 472533 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.4038. Min Act: -0.1700

Data Index: 6891840 (Open Web Text)

Max Activating Token Index: 295

Text #2

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.3548. Min Act: -0.1700

Data Index: 4383979 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.3700. Min Act: -0.1700

Data Index: 276828 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.3198. Min Act: -0.1700

Data Index: 1781804 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.3437. Min Act: -0.1700

Data Index: 6483120 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.3388. Min Act: -0.1700

Data Index: 4803424 (Open Web Text)

Max Activating Token Index: 501

Text #7

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.3134. Min Act: -0.1700

Data Index: 7901861 (Open Web Text)

Max Activating Token Index: 311

Text #8

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2903. Min Act: -0.1700

Data Index: 6489095 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2806. Min Act: -0.1700

Data Index: 7361913 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2968. Min Act: -0.1700

Data Index: 2749311 (Open Web Text)

Max Activating Token Index: 963

Text #11

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2531. Min Act: -0.1700

Data Index: 6101425 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2801. Min Act: -0.1700

Data Index: 5652087 (Open Web Text)

Max Activating Token Index: 541

Text #13

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2875. Min Act: -0.1700

Data Index: 3566953 (Open Web Text)

Max Activating Token Index: 219

Text #14

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2618. Min Act: -0.1700

Data Index: 7881686 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2452. Min Act: -0.1700

Data Index: 461802 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2746. Min Act: -0.1700

Data Index: 1705151 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2451. Min Act: -0.1700

Data Index: 4271563 (Open Web Text)

Max Activating Token Index: 615

Text #18

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2321. Min Act: -0.1700

Data Index: 5594111 (Open Web Text)

Max Activating Token Index: 461

Text #19

Max Range: 4.4454. Min Range: -4.4454

Max Act: 4.2447. Min Act: -0.1700

Data Index: 5744899 (Open Web Text)

Max Activating Token Index: 243