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

Dataset: Open Web Text

Neuron 1370 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: 4.2909. Min Range: -4.2909

Max Act: 4.2909. Min Act: -0.1700

Data Index: 6148298 (Open Web Text)

Max Activating Token Index: 119

Text #1

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.2605. Min Act: -0.1700

Data Index: 2507928 (Open Web Text)

Max Activating Token Index: 322

Text #2

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.2148. Min Act: -0.1700

Data Index: 1998693 (Open Web Text)

Max Activating Token Index: 85

Text #3

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.1819. Min Act: -0.1700

Data Index: 7452804 (Open Web Text)

Max Activating Token Index: 372

Text #4

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.1623. Min Act: -0.1700

Data Index: 5797976 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.1109. Min Act: -0.1700

Data Index: 1311138 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.1395. Min Act: -0.1700

Data Index: 3064066 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.1414. Min Act: -0.1700

Data Index: 5361188 (Open Web Text)

Max Activating Token Index: 494

Text #8

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0973. Min Act: -0.1700

Data Index: 5199317 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0874. Min Act: -0.1700

Data Index: 8230650 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0903. Min Act: -0.1700

Data Index: 5635776 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0894. Min Act: -0.1700

Data Index: 6802929 (Open Web Text)

Max Activating Token Index: 804

Text #12

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0754. Min Act: -0.1700

Data Index: 7994165 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0760. Min Act: -0.1700

Data Index: 5149518 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0444. Min Act: -0.1700

Data Index: 5978848 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0455. Min Act: -0.1700

Data Index: 5001368 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0281. Min Act: -0.1700

Data Index: 5936517 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0486. Min Act: -0.1700

Data Index: 1901320 (Open Web Text)

Max Activating Token Index: 171

Text #18

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0268. Min Act: -0.1700

Data Index: 6551450 (Open Web Text)

Max Activating Token Index: 993

Text #19

Max Range: 4.2909. Min Range: -4.2909

Max Act: 4.0506. Min Act: -0.1700

Data Index: 5053437 (Open Web Text)

Max Activating Token Index: 347