Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 5667 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.8320. Min Act: -0.1700

Data Index: 5561241 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.3632. Min Act: -0.1700

Data Index: 5834955 (Open Web Text)

Max Activating Token Index: 605

Text #2

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2695. Min Act: -0.1700

Data Index: 6580906 (Open Web Text)

Max Activating Token Index: 298

Text #3

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2382. Min Act: -0.1700

Data Index: 4829285 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1757. Min Act: -0.1700

Data Index: 5171772 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1757. Min Act: -0.1700

Data Index: 8307045 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1757. Min Act: -0.1700

Data Index: 541861 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1445. Min Act: -0.1700

Data Index: 2482732 (Open Web Text)

Max Activating Token Index: 985

Text #8

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1132. Min Act: -0.1700

Data Index: 5644432 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1132. Min Act: -0.1700

Data Index: 6000993 (Open Web Text)

Max Activating Token Index: 572

Text #10

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1132. Min Act: -0.1700

Data Index: 3237622 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0820. Min Act: -0.1700

Data Index: 3459755 (Open Web Text)

Max Activating Token Index: 596

Text #12

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0820. Min Act: -0.1700

Data Index: 1297935 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0507. Min Act: -0.1700

Data Index: 8453645 (Open Web Text)

Max Activating Token Index: 877

Text #14

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0507. Min Act: -0.1700

Data Index: 5306664 (Open Web Text)

Max Activating Token Index: 324

Text #15

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0820. Min Act: -0.1700

Data Index: 8778676 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0195. Min Act: -0.1700

Data Index: 2402479 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0195. Min Act: -0.1700

Data Index: 8744203 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.0507. Min Act: -0.1700

Data Index: 558437 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 5.8320. Min Range: -5.8320

Max Act: 4.9882. Min Act: -0.1700

Data Index: 2051758 (Open Web Text)

Max Activating Token Index: 986