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

Dataset: Open Web Text

Neuron 1594 in Layer 0

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: 1.0735. Min Range: -1.0735

Max Act: 1.0735. Min Act: -0.1240

Data Index: 4230000 (Open Web Text)

Max Activating Token Index: 982

Text #1

Max Range: 1.0735. Min Range: -1.0735

Max Act: 1.0544. Min Act: -0.0145

Data Index: 4230001 (Open Web Text)

Max Activating Token Index: 955

Text #2

Max Range: 1.0735. Min Range: -1.0735

Max Act: 1.0244. Min Act: -0.0473

Data Index: 4229988 (Open Web Text)

Max Activating Token Index: 972

Text #3

Max Range: 1.0735. Min Range: -1.0735

Max Act: 1.0116. Min Act: 0.0488

Data Index: 4229995 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 1.0735. Min Range: -1.0735

Max Act: 1.0022. Min Act: 0.0389

Data Index: 4229999 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9971. Min Act: -0.0683

Data Index: 404323 (Open Web Text)

Max Activating Token Index: 716

Text #6

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9844. Min Act: 0.0084

Data Index: 4229996 (Open Web Text)

Max Activating Token Index: 983

Text #7

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9649. Min Act: -0.0945

Data Index: 4230004 (Open Web Text)

Max Activating Token Index: 929

Text #8

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9655. Min Act: -0.0897

Data Index: 6976708 (Open Web Text)

Max Activating Token Index: 822

Text #9

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9542. Min Act: -0.0646

Data Index: 7494640 (Open Web Text)

Max Activating Token Index: 817

Text #10

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9513. Min Act: 0.0278

Data Index: 4230002 (Open Web Text)

Max Activating Token Index: 906

Text #11

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9465. Min Act: -0.0530

Data Index: 4229993 (Open Web Text)

Max Activating Token Index: 971

Text #12

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9396. Min Act: -0.0822

Data Index: 3262851 (Open Web Text)

Max Activating Token Index: 261

Text #13

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9390. Min Act: 0.0093

Data Index: 4229990 (Open Web Text)

Max Activating Token Index: 898

Text #14

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9394. Min Act: -0.0984

Data Index: 4534674 (Open Web Text)

Max Activating Token Index: 245

Text #15

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9360. Min Act: -0.0222

Data Index: 4229994 (Open Web Text)

Max Activating Token Index: 953

Text #16

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9399. Min Act: 0.0095

Data Index: 4229998 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9370. Min Act: -0.1139

Data Index: 988781 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9368. Min Act: -0.0911

Data Index: 6384472 (Open Web Text)

Max Activating Token Index: 254

Text #19

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9277. Min Act: -0.1237

Data Index: 3228033 (Open Web Text)

Max Activating Token Index: 748