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

Dataset: Open Web Text

Neuron 1053 in Layer 0

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: 6.1290. Min Range: -6.1290

Max Act: 6.1290. Min Act: -0.1700

Data Index: 123198 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.9133. Min Act: -0.1700

Data Index: 1861882 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.9038. Min Act: -0.1700

Data Index: 8776148 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.8785. Min Act: -0.1700

Data Index: 3160394 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.8500. Min Act: -0.1700

Data Index: 8327520 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.8496. Min Act: -0.1700

Data Index: 3049369 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.8394. Min Act: -0.1700

Data Index: 2015967 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.8016. Min Act: -0.1700

Data Index: 647323 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7833. Min Act: -0.1700

Data Index: 4669920 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7934. Min Act: -0.1700

Data Index: 541264 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7894. Min Act: -0.1700

Data Index: 3301198 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7558. Min Act: -0.1700

Data Index: 5986454 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7452. Min Act: -0.1700

Data Index: 8755985 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7383. Min Act: -0.1700

Data Index: 601477 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7452. Min Act: -0.1700

Data Index: 8581922 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7452. Min Act: -0.1700

Data Index: 7632941 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7740. Min Act: -0.1700

Data Index: 5358515 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7263. Min Act: -0.1700

Data Index: 1304944 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7106. Min Act: -0.1700

Data Index: 6153264 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 6.1290. Min Range: -6.1290

Max Act: 5.7411. Min Act: -0.1700

Data Index: 452264 (Open Web Text)

Max Activating Token Index: 5