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

Dataset: Open Web Text

Neuron 1413 in Layer 2

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: 3.2145. Min Range: -3.2145

Max Act: 3.2145. Min Act: -0.1700

Data Index: 1914514 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.1548. Min Act: -0.1700

Data Index: 819438 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.1336. Min Act: -0.1700

Data Index: 7623853 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0897. Min Act: -0.1700

Data Index: 999153 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0770. Min Act: -0.1700

Data Index: 1042691 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0448. Min Act: -0.1700

Data Index: 6924607 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0453. Min Act: -0.1700

Data Index: 1377231 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0464. Min Act: -0.1700

Data Index: 4828405 (Open Web Text)

Max Activating Token Index: 631

Text #8

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0321. Min Act: -0.1700

Data Index: 482232 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0158. Min Act: -0.1700

Data Index: 4808097 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0026. Min Act: -0.1700

Data Index: 232386 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.2145. Min Range: -3.2145

Max Act: 3.0022. Min Act: -0.1700

Data Index: 3092943 (Open Web Text)

Max Activating Token Index: 344

Text #12

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9915. Min Act: -0.1700

Data Index: 7554686 (Open Web Text)

Max Activating Token Index: 36

Text #13

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9831. Min Act: -0.1700

Data Index: 2022388 (Open Web Text)

Max Activating Token Index: 573

Text #14

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9572. Min Act: -0.1700

Data Index: 8644571 (Open Web Text)

Max Activating Token Index: 36

Text #15

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9711. Min Act: -0.1700

Data Index: 6172841 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9507. Min Act: -0.1700

Data Index: 1672127 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9787. Min Act: -0.1700

Data Index: 4127540 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9554. Min Act: -0.1700

Data Index: 7869288 (Open Web Text)

Max Activating Token Index: 41

Text #19

Max Range: 3.2145. Min Range: -3.2145

Max Act: 2.9375. Min Act: -0.1700

Data Index: 8068249 (Open Web Text)

Max Activating Token Index: 18