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

Dataset: Open Web Text

Neuron 1497 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: 4.2594. Min Range: -4.2594

Max Act: 4.2594. Min Act: -0.1700

Data Index: 5744279 (Open Web Text)

Max Activating Token Index: 134

Text #1

Max Range: 4.2594. Min Range: -4.2594

Max Act: 4.0897. Min Act: -0.1700

Data Index: 478552 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.9622. Min Act: -0.1700

Data Index: 6132932 (Open Web Text)

Max Activating Token Index: 760

Text #3

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.8991. Min Act: -0.1700

Data Index: 3145183 (Open Web Text)

Max Activating Token Index: 534

Text #4

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.8859. Min Act: -0.1700

Data Index: 4855609 (Open Web Text)

Max Activating Token Index: 393

Text #5

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.8457. Min Act: -0.1700

Data Index: 46381 (Open Web Text)

Max Activating Token Index: 154

Text #6

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.8012. Min Act: -0.1700

Data Index: 5771687 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.8150. Min Act: -0.1700

Data Index: 3340004 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.8174. Min Act: -0.1700

Data Index: 6915641 (Open Web Text)

Max Activating Token Index: 200

Text #9

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7752. Min Act: -0.1700

Data Index: 472788 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7595. Min Act: -0.1700

Data Index: 5838626 (Open Web Text)

Max Activating Token Index: 212

Text #11

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7579. Min Act: -0.1700

Data Index: 126839 (Open Web Text)

Max Activating Token Index: 838

Text #12

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7720. Min Act: -0.1700

Data Index: 167138 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7627. Min Act: -0.1700

Data Index: 1494657 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7968. Min Act: -0.1700

Data Index: 8583762 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7602. Min Act: -0.1700

Data Index: 1428991 (Open Web Text)

Max Activating Token Index: 361

Text #16

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7602. Min Act: -0.1700

Data Index: 107604 (Open Web Text)

Max Activating Token Index: 146

Text #17

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7320. Min Act: -0.1700

Data Index: 2294038 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.6667. Min Act: -0.1700

Data Index: 265314 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 4.2594. Min Range: -4.2594

Max Act: 3.7055. Min Act: -0.1700

Data Index: 4532014 (Open Web Text)

Max Activating Token Index: 1021