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

Dataset: Open Web Text

Neuron 2521 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: 3.0864. Min Range: -3.0864

Max Act: 3.0790. Min Act: -0.1700

Data Index: 8108269 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0585. Min Act: -0.1700

Data Index: 5651095 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0821. Min Act: -0.1700

Data Index: 6321359 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0864. Min Act: -0.1700

Data Index: 7114533 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0534. Min Act: -0.1700

Data Index: 7047484 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0692. Min Act: -0.1700

Data Index: 6918556 (Open Web Text)

Max Activating Token Index: 982

Text #6

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0767. Min Act: -0.1700

Data Index: 5916367 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0566. Min Act: -0.1700

Data Index: 6864710 (Open Web Text)

Max Activating Token Index: 920

Text #8

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9801. Min Act: -0.1700

Data Index: 7565465 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0281. Min Act: -0.1700

Data Index: 5144891 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0538. Min Act: -0.1700

Data Index: 1757575 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9526. Min Act: -0.1700

Data Index: 4560164 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9569. Min Act: -0.1700

Data Index: 7858229 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 3.0864. Min Range: -3.0864

Max Act: 3.0094. Min Act: -0.1700

Data Index: 6203217 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9502. Min Act: -0.1700

Data Index: 479547 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9709. Min Act: -0.1700

Data Index: 2364568 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9734. Min Act: -0.1700

Data Index: 8194508 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9604. Min Act: -0.1700

Data Index: 4295929 (Open Web Text)

Max Activating Token Index: 955

Text #18

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9594. Min Act: -0.1700

Data Index: 5908465 (Open Web Text)

Max Activating Token Index: 979

Text #19

Max Range: 3.0864. Min Range: -3.0864

Max Act: 2.9475. Min Act: -0.1700

Data Index: 6127126 (Open Web Text)

Max Activating Token Index: 211