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

Dataset: Open Web Text

Neuron 572 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: 5.8835. Min Range: -5.8835

Max Act: 5.8835. Min Act: -0.1700

Data Index: 4361417 (Open Web Text)

Max Activating Token Index: 649

Text #1

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7969. Min Act: -0.1700

Data Index: 5634880 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7592. Min Act: -0.1700

Data Index: 4179524 (Open Web Text)

Max Activating Token Index: 435

Text #3

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7271. Min Act: -0.1700

Data Index: 8125474 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7510. Min Act: -0.1700

Data Index: 8811098 (Open Web Text)

Max Activating Token Index: 1004

Text #5

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7358. Min Act: -0.1700

Data Index: 697086 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6999. Min Act: -0.1700

Data Index: 6316746 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7384. Min Act: -0.1700

Data Index: 3181285 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7435. Min Act: -0.1700

Data Index: 5376657 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6737. Min Act: -0.1700

Data Index: 1994069 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.7248. Min Act: -0.1700

Data Index: 1782710 (Open Web Text)

Max Activating Token Index: 716

Text #11

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6876. Min Act: -0.1700

Data Index: 8624445 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6215. Min Act: -0.1700

Data Index: 3447467 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6509. Min Act: -0.1700

Data Index: 3446319 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6686. Min Act: -0.1700

Data Index: 5242599 (Open Web Text)

Max Activating Token Index: 997

Text #15

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6209. Min Act: -0.1700

Data Index: 282647 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6401. Min Act: -0.1700

Data Index: 2705080 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.5914. Min Act: -0.1700

Data Index: 1628958 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6149. Min Act: -0.1700

Data Index: 6265584 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 5.8835. Min Range: -5.8835

Max Act: 5.6291. Min Act: -0.1700

Data Index: 3950871 (Open Web Text)

Max Activating Token Index: 522