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

Dataset: Open Web Text

Neuron 3053 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: 1.8112. Min Range: -1.8112

Max Act: 1.8112. Min Act: -0.1700

Data Index: 7113018 (Open Web Text)

Max Activating Token Index: 161

Text #1

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7963. Min Act: -0.1699

Data Index: 7102695 (Open Web Text)

Max Activating Token Index: 409

Text #2

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7927. Min Act: -0.1700

Data Index: 7982757 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7954. Min Act: -0.1700

Data Index: 147560 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7871. Min Act: -0.1700

Data Index: 4674224 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7750. Min Act: -0.1700

Data Index: 3082853 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7788. Min Act: -0.1700

Data Index: 4062902 (Open Web Text)

Max Activating Token Index: 385

Text #7

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7839. Min Act: -0.1700

Data Index: 7199768 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7688. Min Act: -0.1700

Data Index: 8009941 (Open Web Text)

Max Activating Token Index: 925

Text #9

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7538. Min Act: -0.1700

Data Index: 8567996 (Open Web Text)

Max Activating Token Index: 532

Text #10

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7706. Min Act: -0.1700

Data Index: 748898 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7628. Min Act: -0.1700

Data Index: 3115257 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7583. Min Act: -0.1699

Data Index: 1117834 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7596. Min Act: -0.1700

Data Index: 6989105 (Open Web Text)

Max Activating Token Index: 525

Text #14

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7510. Min Act: -0.1700

Data Index: 4993015 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7553. Min Act: -0.1699

Data Index: 6325856 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7544. Min Act: -0.1700

Data Index: 1851589 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7567. Min Act: -0.1700

Data Index: 3371657 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7468. Min Act: -0.1700

Data Index: 6845748 (Open Web Text)

Max Activating Token Index: 733

Text #19

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.7454. Min Act: -0.1700

Data Index: 2348680 (Open Web Text)

Max Activating Token Index: 456