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

Dataset: Open Web Text

Neuron 1342 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: 5.0248. Min Range: -5.0248

Max Act: 5.0248. Min Act: -0.1700

Data Index: 5855725 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.9600. Min Act: -0.1700

Data Index: 731589 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.9510. Min Act: -0.1700

Data Index: 4939678 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.8538. Min Act: -0.1700

Data Index: 2189323 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.8113. Min Act: -0.1700

Data Index: 3792815 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.8221. Min Act: -0.1700

Data Index: 7977331 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7862. Min Act: -0.1700

Data Index: 8183301 (Open Web Text)

Max Activating Token Index: 571

Text #7

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7932. Min Act: -0.1700

Data Index: 1253644 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7711. Min Act: -0.1700

Data Index: 6897595 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7879. Min Act: -0.1700

Data Index: 1794485 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7580. Min Act: -0.1700

Data Index: 3903857 (Open Web Text)

Max Activating Token Index: 502

Text #11

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7862. Min Act: -0.1700

Data Index: 5651862 (Open Web Text)

Max Activating Token Index: 1011

Text #12

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7658. Min Act: -0.1700

Data Index: 303537 (Open Web Text)

Max Activating Token Index: 308

Text #13

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7658. Min Act: -0.1700

Data Index: 5392759 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7649. Min Act: -0.1700

Data Index: 2546008 (Open Web Text)

Max Activating Token Index: 941

Text #15

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7769. Min Act: -0.1700

Data Index: 6906798 (Open Web Text)

Max Activating Token Index: 136

Text #16

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.8110. Min Act: -0.1700

Data Index: 6053538 (Open Web Text)

Max Activating Token Index: 722

Text #17

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7549. Min Act: -0.1700

Data Index: 3267451 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7505. Min Act: -0.1700

Data Index: 5497622 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 5.0248. Min Range: -5.0248

Max Act: 4.7538. Min Act: -0.1700

Data Index: 4442562 (Open Web Text)

Max Activating Token Index: 486