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

Dataset: Open Web Text

Neuron 639 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: 4.3501. Min Range: -4.3501

Max Act: 4.3501. Min Act: -0.1700

Data Index: 3128402 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.2500. Min Act: -0.1700

Data Index: 1766285 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.2147. Min Act: -0.1700

Data Index: 1469350 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.2156. Min Act: -0.1700

Data Index: 287091 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.2257. Min Act: -0.1700

Data Index: 5713915 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.2181. Min Act: -0.1700

Data Index: 1348023 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1797. Min Act: -0.1700

Data Index: 2912352 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1822. Min Act: -0.1700

Data Index: 7475368 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1509. Min Act: -0.1700

Data Index: 4409890 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1408. Min Act: -0.1700

Data Index: 4785401 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1372. Min Act: -0.1700

Data Index: 3193202 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1197. Min Act: -0.1700

Data Index: 4549602 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1331. Min Act: -0.1700

Data Index: 944585 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1261. Min Act: -0.1700

Data Index: 8219415 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1239. Min Act: -0.1700

Data Index: 1727335 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1235. Min Act: -0.1700

Data Index: 7326781 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1380. Min Act: -0.1700

Data Index: 6560321 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1354. Min Act: -0.1700

Data Index: 1602611 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.1163. Min Act: -0.1700

Data Index: 6238683 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.3501. Min Range: -4.3501

Max Act: 4.0858. Min Act: -0.1700

Data Index: 1802802 (Open Web Text)

Max Activating Token Index: 3