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

Dataset: Open Web Text

Neuron 495 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: 4.2243. Min Range: -4.2243

Max Act: 4.2243. Min Act: -0.1700

Data Index: 1441270 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.2134. Min Act: -0.1700

Data Index: 5732962 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1881. Min Act: -0.1700

Data Index: 2702555 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1683. Min Act: -0.1700

Data Index: 3597924 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1432. Min Act: -0.1700

Data Index: 4014124 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1269. Min Act: -0.1700

Data Index: 3654302 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1464. Min Act: -0.1700

Data Index: 1383241 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1531. Min Act: -0.1700

Data Index: 4108261 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1501. Min Act: -0.1700

Data Index: 6906313 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1588. Min Act: -0.1700

Data Index: 4159152 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.0983. Min Act: -0.1700

Data Index: 2696637 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1271. Min Act: -0.1700

Data Index: 6291392 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1124. Min Act: -0.1700

Data Index: 2194044 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1174. Min Act: -0.1700

Data Index: 1624467 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1151. Min Act: -0.1700

Data Index: 3332530 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.1034. Min Act: -0.1700

Data Index: 6848415 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.0839. Min Act: -0.1700

Data Index: 4992301 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.0822. Min Act: -0.1700

Data Index: 1731369 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.0769. Min Act: -0.1700

Data Index: 3357799 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.2243. Min Range: -4.2243

Max Act: 4.0760. Min Act: -0.1700

Data Index: 4013522 (Open Web Text)

Max Activating Token Index: 5