Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 3093 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.8320. Min Act: -0.1700

Data Index: 1455190 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7225. Min Act: -0.1700

Data Index: 7741088 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7069. Min Act: -0.1700

Data Index: 8298345 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6913. Min Act: -0.1700

Data Index: 7236970 (Open Web Text)

Max Activating Token Index: 197

Text #4

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6913. Min Act: -0.1700

Data Index: 3117104 (Open Web Text)

Max Activating Token Index: 535

Text #5

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6756. Min Act: -0.1700

Data Index: 172611 (Open Web Text)

Max Activating Token Index: 568

Text #6

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6600. Min Act: -0.1700

Data Index: 2120159 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6443. Min Act: -0.1700

Data Index: 1001340 (Open Web Text)

Max Activating Token Index: 129

Text #8

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6287. Min Act: -0.1700

Data Index: 198992 (Open Web Text)

Max Activating Token Index: 624

Text #9

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6287. Min Act: -0.1700

Data Index: 7374297 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1440656 (Open Web Text)

Max Activating Token Index: 844

Text #11

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1336641 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5974. Min Act: -0.1700

Data Index: 8274665 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5974. Min Act: -0.1700

Data Index: 7056176 (Open Web Text)

Max Activating Token Index: 880

Text #14

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5974. Min Act: -0.1700

Data Index: 2991071 (Open Web Text)

Max Activating Token Index: 347

Text #15

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5504. Min Act: -0.1700

Data Index: 7456831 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5504. Min Act: -0.1700

Data Index: 6674384 (Open Web Text)

Max Activating Token Index: 362

Text #17

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5661. Min Act: -0.1700

Data Index: 5355717 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5347. Min Act: -0.1700

Data Index: 2775259 (Open Web Text)

Max Activating Token Index: 603

Text #19

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5191. Min Act: -0.1700

Data Index: 5411616 (Open Web Text)

Max Activating Token Index: 519