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

Dataset: Open Web Text

Neuron 1681 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: 5.7859. Min Range: -5.7859

Max Act: 5.7859. Min Act: -0.1700

Data Index: 5821320 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7786. Min Act: -0.1700

Data Index: 8266598 (Open Web Text)

Max Activating Token Index: 945

Text #2

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7389. Min Act: -0.1700

Data Index: 1603052 (Open Web Text)

Max Activating Token Index: 980

Text #3

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7760. Min Act: -0.1700

Data Index: 6135761 (Open Web Text)

Max Activating Token Index: 829

Text #4

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7628. Min Act: -0.1700

Data Index: 1929985 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7365. Min Act: -0.1700

Data Index: 4529549 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7017. Min Act: -0.1700

Data Index: 4964875 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7341. Min Act: -0.1700

Data Index: 1400504 (Open Web Text)

Max Activating Token Index: 855

Text #8

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.7201. Min Act: -0.1700

Data Index: 4302063 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6627. Min Act: -0.1700

Data Index: 6378381 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6776. Min Act: -0.1700

Data Index: 3251844 (Open Web Text)

Max Activating Token Index: 995

Text #11

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6559. Min Act: -0.1700

Data Index: 6700938 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6747. Min Act: -0.1700

Data Index: 5430209 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6384. Min Act: -0.1700

Data Index: 7158870 (Open Web Text)

Max Activating Token Index: 523

Text #14

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6329. Min Act: -0.1700

Data Index: 2955486 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6569. Min Act: -0.1700

Data Index: 6034046 (Open Web Text)

Max Activating Token Index: 662

Text #16

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6142. Min Act: -0.1700

Data Index: 2339050 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6194. Min Act: -0.1700

Data Index: 1700038 (Open Web Text)

Max Activating Token Index: 401

Text #18

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.6008. Min Act: -0.1700

Data Index: 5090390 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 5.7859. Min Range: -5.7859

Max Act: 5.5952. Min Act: -0.1700

Data Index: 451300 (Open Web Text)

Max Activating Token Index: 832