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

Dataset: Open Web Text

Neuron 928 in Layer 6

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: 4.2601. Min Range: -4.2601

Max Act: 4.2601. Min Act: -0.1700

Data Index: 7934670 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1574. Min Act: -0.1700

Data Index: 8521746 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1372. Min Act: -0.1700

Data Index: 6799691 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1244. Min Act: -0.1700

Data Index: 3433577 (Open Web Text)

Max Activating Token Index: 599

Text #4

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0828. Min Act: -0.1700

Data Index: 377409 (Open Web Text)

Max Activating Token Index: 941

Text #5

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0680. Min Act: -0.1700

Data Index: 5687657 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0908. Min Act: -0.1700

Data Index: 3101858 (Open Web Text)

Max Activating Token Index: 778

Text #7

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0225. Min Act: -0.1700

Data Index: 4135988 (Open Web Text)

Max Activating Token Index: 348

Text #8

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0125. Min Act: -0.1700

Data Index: 7112324 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9869. Min Act: -0.1700

Data Index: 2251284 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0183. Min Act: -0.1700

Data Index: 350229 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9601. Min Act: -0.1700

Data Index: 553738 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9498. Min Act: -0.1700

Data Index: 3891614 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9156. Min Act: -0.1700

Data Index: 6100933 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9450. Min Act: -0.1700

Data Index: 7141019 (Open Web Text)

Max Activating Token Index: 1000

Text #15

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9356. Min Act: -0.1700

Data Index: 1563420 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9327. Min Act: -0.1700

Data Index: 5550890 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9456. Min Act: -0.1700

Data Index: 5646458 (Open Web Text)

Max Activating Token Index: 114

Text #18

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9432. Min Act: -0.1700

Data Index: 7881178 (Open Web Text)

Max Activating Token Index: 219

Text #19

Max Range: 4.2601. Min Range: -4.2601

Max Act: 3.9298. Min Act: -0.1700

Data Index: 107066 (Open Web Text)

Max Activating Token Index: 497