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

Dataset: Open Web Text

Neuron 120 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: 3.0125. Min Range: -3.0125

Max Act: 3.0125. Min Act: -0.1700

Data Index: 6158593 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.9626. Min Act: -0.1700

Data Index: 8544153 (Open Web Text)

Max Activating Token Index: 440

Text #2

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.9176. Min Act: -0.1700

Data Index: 7112614 (Open Web Text)

Max Activating Token Index: 704

Text #3

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.8989. Min Act: -0.1700

Data Index: 136847 (Open Web Text)

Max Activating Token Index: 130

Text #4

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.8585. Min Act: -0.1700

Data Index: 463508 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.8374. Min Act: -0.1700

Data Index: 3619408 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.8563. Min Act: -0.1700

Data Index: 609247 (Open Web Text)

Max Activating Token Index: 741

Text #7

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7996. Min Act: -0.1700

Data Index: 1727941 (Open Web Text)

Max Activating Token Index: 859

Text #8

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7843. Min Act: -0.1700

Data Index: 3710752 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7888. Min Act: -0.1700

Data Index: 7842895 (Open Web Text)

Max Activating Token Index: 920

Text #10

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7719. Min Act: -0.1700

Data Index: 5140990 (Open Web Text)

Max Activating Token Index: 763

Text #11

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7586. Min Act: -0.1700

Data Index: 5696748 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7560. Min Act: -0.1700

Data Index: 6348498 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7732. Min Act: -0.1700

Data Index: 2975759 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7487. Min Act: -0.1700

Data Index: 2140742 (Open Web Text)

Max Activating Token Index: 108

Text #15

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7562. Min Act: -0.1700

Data Index: 5736665 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7516. Min Act: -0.1700

Data Index: 2461941 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7541. Min Act: -0.1700

Data Index: 1499297 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7520. Min Act: -0.1700

Data Index: 3504560 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7613. Min Act: -0.1700

Data Index: 1146652 (Open Web Text)

Max Activating Token Index: 496