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

Dataset: Open Web Text

Neuron 2912 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: 3.7672. Min Range: -3.7672

Max Act: 3.7672. Min Act: -0.1700

Data Index: 6816994 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.7139. Min Act: -0.1700

Data Index: 4541723 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.6697. Min Act: -0.1700

Data Index: 5979295 (Open Web Text)

Max Activating Token Index: 287

Text #3

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.6811. Min Act: -0.1700

Data Index: 5979294 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.6863. Min Act: -0.1700

Data Index: 2701214 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.6480. Min Act: -0.1700

Data Index: 3676558 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.6584. Min Act: -0.1700

Data Index: 4708559 (Open Web Text)

Max Activating Token Index: 97

Text #7

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.6214. Min Act: -0.1700

Data Index: 7779272 (Open Web Text)

Max Activating Token Index: 89

Text #8

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.6062. Min Act: -0.1700

Data Index: 5800968 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5843. Min Act: -0.1700

Data Index: 4263809 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5937. Min Act: -0.1700

Data Index: 1698025 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5877. Min Act: -0.1700

Data Index: 4013355 (Open Web Text)

Max Activating Token Index: 144

Text #12

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5518. Min Act: -0.1700

Data Index: 8786046 (Open Web Text)

Max Activating Token Index: 135

Text #13

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5744. Min Act: -0.1700

Data Index: 3187706 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5694. Min Act: -0.1700

Data Index: 541473 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5755. Min Act: -0.1700

Data Index: 316351 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5595. Min Act: -0.1700

Data Index: 462110 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5635. Min Act: -0.1700

Data Index: 151910 (Open Web Text)

Max Activating Token Index: 234

Text #18

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5391. Min Act: -0.1700

Data Index: 7557584 (Open Web Text)

Max Activating Token Index: 538

Text #19

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.5302. Min Act: -0.1700

Data Index: 1975532 (Open Web Text)

Max Activating Token Index: 501