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

Dataset: Open Web Text

Neuron 1342 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: 5.1291. Min Range: -5.1291

Max Act: 5.1291. Min Act: -0.1700

Data Index: 7935695 (Open Web Text)

Max Activating Token Index: 432

Text #1

Max Range: 5.1291. Min Range: -5.1291

Max Act: 5.1250. Min Act: -0.1700

Data Index: 8167983 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 5.1291. Min Range: -5.1291

Max Act: 5.0354. Min Act: -0.1700

Data Index: 2617242 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.9789. Min Act: -0.1700

Data Index: 442060 (Open Web Text)

Max Activating Token Index: 954

Text #4

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.9716. Min Act: -0.1700

Data Index: 6922940 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.9011. Min Act: -0.1700

Data Index: 6749384 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.8834. Min Act: -0.1700

Data Index: 5053431 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.8767. Min Act: -0.1700

Data Index: 2414339 (Open Web Text)

Max Activating Token Index: 530

Text #8

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.8214. Min Act: -0.1700

Data Index: 3333623 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7782. Min Act: -0.1700

Data Index: 5582429 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7946. Min Act: -0.1700

Data Index: 5653507 (Open Web Text)

Max Activating Token Index: 811

Text #11

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7864. Min Act: -0.1700

Data Index: 5855187 (Open Web Text)

Max Activating Token Index: 133

Text #12

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7646. Min Act: -0.1700

Data Index: 2224024 (Open Web Text)

Max Activating Token Index: 242

Text #13

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7833. Min Act: -0.1700

Data Index: 7153991 (Open Web Text)

Max Activating Token Index: 862

Text #14

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7787. Min Act: -0.1700

Data Index: 1178880 (Open Web Text)

Max Activating Token Index: 496

Text #15

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7912. Min Act: -0.1700

Data Index: 2317637 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.8043. Min Act: -0.1700

Data Index: 4769872 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7075. Min Act: -0.1700

Data Index: 6857829 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7147. Min Act: -0.1700

Data Index: 2771929 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 5.1291. Min Range: -5.1291

Max Act: 4.7501. Min Act: -0.1700

Data Index: 5070028 (Open Web Text)

Max Activating Token Index: 910