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

Dataset: Open Web Text

Neuron 3042 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: 1.1738. Min Range: -1.1738

Max Act: 1.1738. Min Act: -0.1700

Data Index: 5911642 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1279. Min Act: -0.1700

Data Index: 6169352 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1338. Min Act: -0.1700

Data Index: 6316929 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1429. Min Act: -0.1700

Data Index: 7542178 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1143. Min Act: -0.1700

Data Index: 4469141 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1218. Min Act: -0.1700

Data Index: 4364031 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1170. Min Act: -0.1700

Data Index: 8725505 (Open Web Text)

Max Activating Token Index: 71

Text #7

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1123. Min Act: -0.1700

Data Index: 438633 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1042. Min Act: -0.1700

Data Index: 2695574 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1102. Min Act: -0.1700

Data Index: 932494 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1063. Min Act: -0.1700

Data Index: 3061422 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1069. Min Act: -0.1700

Data Index: 8778696 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.0996. Min Act: -0.1700

Data Index: 3486716 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.0892. Min Act: -0.1700

Data Index: 7769945 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1117. Min Act: -0.1700

Data Index: 3468747 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1020. Min Act: -0.1700

Data Index: 6514889 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1072. Min Act: -0.1700

Data Index: 6170895 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.0872. Min Act: -0.1700

Data Index: 1526350 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.0979. Min Act: -0.1700

Data Index: 5693043 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.0957. Min Act: -0.1700

Data Index: 4857616 (Open Web Text)

Max Activating Token Index: 4