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

Dataset: Open Web Text

Neuron 2729 in Layer 6

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: 4.7294. Min Range: -4.7294

Max Act: 4.7294. Min Act: -0.1700

Data Index: 68285 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.6740. Min Act: -0.1700

Data Index: 1168805 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.6203. Min Act: -0.1700

Data Index: 4504460 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.5692. Min Act: -0.1700

Data Index: 2198782 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.5675. Min Act: -0.1700

Data Index: 4049554 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.5549. Min Act: -0.1700

Data Index: 4915254 (Open Web Text)

Max Activating Token Index: 242

Text #6

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.5496. Min Act: -0.1700

Data Index: 3018900 (Open Web Text)

Max Activating Token Index: 569

Text #7

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.5512. Min Act: -0.1700

Data Index: 1180836 (Open Web Text)

Max Activating Token Index: 520

Text #8

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4820. Min Act: -0.1700

Data Index: 1916831 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.5175. Min Act: -0.1700

Data Index: 379108 (Open Web Text)

Max Activating Token Index: 159

Text #10

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4982. Min Act: -0.1700

Data Index: 1571460 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4582. Min Act: -0.1700

Data Index: 5118571 (Open Web Text)

Max Activating Token Index: 555

Text #12

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4396. Min Act: -0.1700

Data Index: 657219 (Open Web Text)

Max Activating Token Index: 940

Text #13

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4522. Min Act: -0.1700

Data Index: 8191482 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4574. Min Act: -0.1700

Data Index: 2119890 (Open Web Text)

Max Activating Token Index: 67

Text #15

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4797. Min Act: -0.1700

Data Index: 7653066 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4828. Min Act: -0.1700

Data Index: 5235668 (Open Web Text)

Max Activating Token Index: 220

Text #17

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4755. Min Act: -0.1700

Data Index: 7429956 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4462. Min Act: -0.1700

Data Index: 5222810 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 4.7294. Min Range: -4.7294

Max Act: 4.4682. Min Act: -0.1700

Data Index: 6094021 (Open Web Text)

Max Activating Token Index: 628