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

Dataset: Open Web Text

Neuron 559 in Layer 4

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: 4.7576. Min Range: -4.7576

Max Act: 4.7552. Min Act: -0.1700

Data Index: 4183687 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.7576. Min Act: -0.1700

Data Index: 4146568 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6701. Min Act: -0.1700

Data Index: 5923560 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.7311. Min Act: -0.1700

Data Index: 6847115 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.7026. Min Act: -0.1700

Data Index: 8238620 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6673. Min Act: -0.1700

Data Index: 5647153 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6613. Min Act: -0.1700

Data Index: 1463500 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6754. Min Act: -0.1700

Data Index: 528322 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6686. Min Act: -0.1700

Data Index: 5213505 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6762. Min Act: -0.1700

Data Index: 8596477 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6750. Min Act: -0.1700

Data Index: 6289767 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.5974. Min Act: -0.1700

Data Index: 276004 (Open Web Text)

Max Activating Token Index: 316

Text #12

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6572. Min Act: -0.1700

Data Index: 71468 (Open Web Text)

Max Activating Token Index: 560

Text #13

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6157. Min Act: -0.1700

Data Index: 4433085 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6433. Min Act: -0.1700

Data Index: 4243345 (Open Web Text)

Max Activating Token Index: 243

Text #15

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6286. Min Act: -0.1700

Data Index: 3780717 (Open Web Text)

Max Activating Token Index: 920

Text #16

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6363. Min Act: -0.1700

Data Index: 7184521 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6246. Min Act: -0.1700

Data Index: 2082605 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6320. Min Act: -0.1700

Data Index: 5330152 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 4.7576. Min Range: -4.7576

Max Act: 4.6580. Min Act: -0.1700

Data Index: 5569650 (Open Web Text)

Max Activating Token Index: 404