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

Dataset: Open Web Text

Neuron 465 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: 4.0279. Min Range: -4.0279

Max Act: 4.0279. Min Act: -0.1700

Data Index: 862183 (Open Web Text)

Max Activating Token Index: 560

Text #1

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.8384. Min Act: -0.1700

Data Index: 8338492 (Open Web Text)

Max Activating Token Index: 250

Text #2

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.7817. Min Act: -0.1700

Data Index: 5613981 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.7386. Min Act: -0.1700

Data Index: 8033608 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6691. Min Act: -0.1700

Data Index: 8683712 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6794. Min Act: -0.1700

Data Index: 3877967 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6770. Min Act: -0.1700

Data Index: 5436363 (Open Web Text)

Max Activating Token Index: 638

Text #7

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6156. Min Act: -0.1700

Data Index: 4524549 (Open Web Text)

Max Activating Token Index: 578

Text #8

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6003. Min Act: -0.1700

Data Index: 3206285 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6378. Min Act: -0.1700

Data Index: 4548186 (Open Web Text)

Max Activating Token Index: 304

Text #10

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6172. Min Act: -0.1700

Data Index: 4927136 (Open Web Text)

Max Activating Token Index: 858

Text #11

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5941. Min Act: -0.1700

Data Index: 5081630 (Open Web Text)

Max Activating Token Index: 422

Text #12

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.6168. Min Act: -0.1700

Data Index: 7287426 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5970. Min Act: -0.1700

Data Index: 8552086 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5974. Min Act: -0.1700

Data Index: 5741632 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5753. Min Act: -0.1700

Data Index: 6911904 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5718. Min Act: -0.1700

Data Index: 1348502 (Open Web Text)

Max Activating Token Index: 703

Text #17

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5341. Min Act: -0.1700

Data Index: 8542787 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5280. Min Act: -0.1700

Data Index: 6080739 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 4.0279. Min Range: -4.0279

Max Act: 3.5147. Min Act: -0.1700

Data Index: 3233147 (Open Web Text)

Max Activating Token Index: 358