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

Dataset: Open Web Text

Neuron 922 in Layer 5

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: 6.6242. Min Range: -6.6242

Max Act: 6.6114. Min Act: -0.1700

Data Index: 349990 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.6242. Min Act: -0.1700

Data Index: 8805984 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.5957. Min Act: -0.1700

Data Index: 373622 (Open Web Text)

Max Activating Token Index: 46

Text #3

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.5858. Min Act: -0.1700

Data Index: 1754398 (Open Web Text)

Max Activating Token Index: 391

Text #4

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.5115. Min Act: -0.1700

Data Index: 3038360 (Open Web Text)

Max Activating Token Index: 1006

Text #5

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.5037. Min Act: -0.1700

Data Index: 2484292 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4708. Min Act: -0.1700

Data Index: 3423723 (Open Web Text)

Max Activating Token Index: 139

Text #7

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4698. Min Act: -0.1699

Data Index: 132329 (Open Web Text)

Max Activating Token Index: 1017

Text #8

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.5004. Min Act: -0.1700

Data Index: 6826755 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4616. Min Act: -0.1700

Data Index: 1253939 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4759. Min Act: -0.1700

Data Index: 6669026 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.5015. Min Act: -0.1700

Data Index: 4124408 (Open Web Text)

Max Activating Token Index: 566

Text #12

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4899. Min Act: -0.1700

Data Index: 5754145 (Open Web Text)

Max Activating Token Index: 842

Text #13

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.5033. Min Act: -0.1700

Data Index: 2575434 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4177. Min Act: -0.1700

Data Index: 1934804 (Open Web Text)

Max Activating Token Index: 648

Text #15

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4427. Min Act: -0.1700

Data Index: 4401711 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4610. Min Act: -0.1700

Data Index: 8120074 (Open Web Text)

Max Activating Token Index: 931

Text #17

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4379. Min Act: -0.1700

Data Index: 453996 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4736. Min Act: -0.1700

Data Index: 6676582 (Open Web Text)

Max Activating Token Index: 898

Text #19

Max Range: 6.6242. Min Range: -6.6242

Max Act: 6.4486. Min Act: -0.1700

Data Index: 1622213 (Open Web Text)

Max Activating Token Index: 384