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

Dataset: Open Web Text

Neuron 106 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: 4.7758. Min Range: -4.7758

Max Act: 4.7758. Min Act: -0.1700

Data Index: 4244409 (Open Web Text)

Max Activating Token Index: 432

Text #1

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.7481. Min Act: -0.1700

Data Index: 5612775 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.7179. Min Act: -0.1700

Data Index: 1343731 (Open Web Text)

Max Activating Token Index: 108

Text #3

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.7042. Min Act: -0.1700

Data Index: 3506376 (Open Web Text)

Max Activating Token Index: 262

Text #4

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6591. Min Act: -0.1700

Data Index: 2117416 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6409. Min Act: -0.1700

Data Index: 3847627 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6578. Min Act: -0.1700

Data Index: 6574857 (Open Web Text)

Max Activating Token Index: 626

Text #7

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6430. Min Act: -0.1700

Data Index: 1741601 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6214. Min Act: -0.1700

Data Index: 1954434 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.5929. Min Act: -0.1700

Data Index: 2001144 (Open Web Text)

Max Activating Token Index: 894

Text #10

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6319. Min Act: -0.1700

Data Index: 5966903 (Open Web Text)

Max Activating Token Index: 842

Text #11

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6044. Min Act: -0.1700

Data Index: 3165136 (Open Web Text)

Max Activating Token Index: 246

Text #12

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.5511. Min Act: -0.1700

Data Index: 1153925 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6129. Min Act: -0.1700

Data Index: 7456090 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.6002. Min Act: -0.1700

Data Index: 6358778 (Open Web Text)

Max Activating Token Index: 816

Text #15

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.5702. Min Act: -0.1700

Data Index: 5966902 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.5813. Min Act: -0.1700

Data Index: 5267521 (Open Web Text)

Max Activating Token Index: 941

Text #17

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.5735. Min Act: -0.1700

Data Index: 15426 (Open Web Text)

Max Activating Token Index: 354

Text #18

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.5270. Min Act: -0.1700

Data Index: 4274199 (Open Web Text)

Max Activating Token Index: 716

Text #19

Max Range: 4.7758. Min Range: -4.7758

Max Act: 4.5567. Min Act: -0.1700

Data Index: 4104884 (Open Web Text)

Max Activating Token Index: 500