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

Dataset: Open Web Text

Neuron 1845 in Layer 3

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: 3.9961. Min Range: -3.9961

Max Act: 3.9836. Min Act: -0.1700

Data Index: 1306978 (Open Web Text)

Max Activating Token Index: 521

Text #1

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.9766. Min Act: -0.1700

Data Index: 8584547 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.9961. Min Act: -0.1700

Data Index: 3883188 (Open Web Text)

Max Activating Token Index: 324

Text #3

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.9206. Min Act: -0.1700

Data Index: 4713727 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.9351. Min Act: -0.1700

Data Index: 7396526 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8801. Min Act: -0.1700

Data Index: 6962272 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8982. Min Act: -0.1700

Data Index: 5357642 (Open Web Text)

Max Activating Token Index: 722

Text #7

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.9170. Min Act: -0.1700

Data Index: 929666 (Open Web Text)

Max Activating Token Index: 725

Text #8

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8689. Min Act: -0.1700

Data Index: 3497052 (Open Web Text)

Max Activating Token Index: 647

Text #9

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8398. Min Act: -0.1700

Data Index: 1487501 (Open Web Text)

Max Activating Token Index: 916

Text #10

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8393. Min Act: -0.1700

Data Index: 1355944 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8579. Min Act: -0.1700

Data Index: 6819285 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.9183. Min Act: -0.1700

Data Index: 3227284 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8813. Min Act: -0.1700

Data Index: 1915729 (Open Web Text)

Max Activating Token Index: 627

Text #14

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8316. Min Act: -0.1700

Data Index: 5800803 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8642. Min Act: -0.1700

Data Index: 1421965 (Open Web Text)

Max Activating Token Index: 883

Text #16

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8198. Min Act: -0.1700

Data Index: 3200040 (Open Web Text)

Max Activating Token Index: 834

Text #17

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8218. Min Act: -0.1700

Data Index: 4112073 (Open Web Text)

Max Activating Token Index: 894

Text #18

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.8729. Min Act: -0.1700

Data Index: 3125007 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 3.9961. Min Range: -3.9961

Max Act: 3.7992. Min Act: -0.1700

Data Index: 4519988 (Open Web Text)

Max Activating Token Index: 433