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

Dataset: Open Web Text

Neuron 1409 in Layer 5

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: 5.1088. Min Range: -5.1088

Max Act: 5.1088. Min Act: -0.1700

Data Index: 1421383 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 5.1088. Min Range: -5.1088

Max Act: 5.0063. Min Act: -0.1700

Data Index: 7690111 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 5.1088. Min Range: -5.1088

Max Act: 5.0046. Min Act: -0.1700

Data Index: 7364636 (Open Web Text)

Max Activating Token Index: 70

Text #3

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9596. Min Act: -0.1700

Data Index: 2650227 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9322. Min Act: -0.1700

Data Index: 180218 (Open Web Text)

Max Activating Token Index: 584

Text #5

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9640. Min Act: -0.1700

Data Index: 5720593 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9219. Min Act: -0.1700

Data Index: 814639 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9268. Min Act: -0.1700

Data Index: 3668431 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9112. Min Act: -0.1700

Data Index: 1198168 (Open Web Text)

Max Activating Token Index: 857

Text #9

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9232. Min Act: -0.1700

Data Index: 3624458 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9062. Min Act: -0.1700

Data Index: 5751660 (Open Web Text)

Max Activating Token Index: 430

Text #11

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9375. Min Act: -0.1700

Data Index: 2089361 (Open Web Text)

Max Activating Token Index: 924

Text #12

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9249. Min Act: -0.1700

Data Index: 2027043 (Open Web Text)

Max Activating Token Index: 733

Text #13

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9385. Min Act: -0.1700

Data Index: 2875705 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9096. Min Act: -0.1700

Data Index: 1728971 (Open Web Text)

Max Activating Token Index: 446

Text #15

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.9216. Min Act: -0.1700

Data Index: 2833152 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.8906. Min Act: -0.1700

Data Index: 1627036 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.8799. Min Act: -0.1700

Data Index: 4111081 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.8945. Min Act: -0.1700

Data Index: 1334345 (Open Web Text)

Max Activating Token Index: 542

Text #19

Max Range: 5.1088. Min Range: -5.1088

Max Act: 4.8951. Min Act: -0.1700

Data Index: 8084924 (Open Web Text)

Max Activating Token Index: 674