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

Dataset: Open Web Text

Neuron 2903 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: 5.2663. Min Range: -5.2663

Max Act: 5.2663. Min Act: -0.1700

Data Index: 4521200 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.2360. Min Act: -0.1700

Data Index: 4924759 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.2052. Min Act: -0.1700

Data Index: 5333281 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.1461. Min Act: -0.1700

Data Index: 4720699 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0855. Min Act: -0.1700

Data Index: 6617443 (Open Web Text)

Max Activating Token Index: 658

Text #5

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0837. Min Act: -0.1700

Data Index: 7138259 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.1031. Min Act: -0.1700

Data Index: 1688845 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.1180. Min Act: -0.1700

Data Index: 3427009 (Open Web Text)

Max Activating Token Index: 53

Text #8

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0790. Min Act: -0.1700

Data Index: 5495983 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0697. Min Act: -0.1700

Data Index: 7913958 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0633. Min Act: -0.1700

Data Index: 2307853 (Open Web Text)

Max Activating Token Index: 327

Text #11

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0504. Min Act: -0.1700

Data Index: 138025 (Open Web Text)

Max Activating Token Index: 615

Text #12

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0835. Min Act: -0.1700

Data Index: 8821661 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0552. Min Act: -0.1700

Data Index: 4824554 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0444. Min Act: -0.1700

Data Index: 996385 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0547. Min Act: -0.1700

Data Index: 6593981 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0366. Min Act: -0.1700

Data Index: 6593716 (Open Web Text)

Max Activating Token Index: 270

Text #17

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0511. Min Act: -0.1700

Data Index: 5656581 (Open Web Text)

Max Activating Token Index: 115

Text #18

Max Range: 5.2663. Min Range: -5.2663

Max Act: 4.9861. Min Act: -0.1700

Data Index: 6360393 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 5.2663. Min Range: -5.2663

Max Act: 5.0311. Min Act: -0.1700

Data Index: 8821315 (Open Web Text)

Max Activating Token Index: 868