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

Dataset: Open Web Text

Neuron 40 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: 3.3648. Min Range: -3.3648

Max Act: 3.3648. Min Act: -0.1700

Data Index: 4743501 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.3567. Min Act: -0.1700

Data Index: 2370559 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.3382. Min Act: -0.1700

Data Index: 3916543 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2822. Min Act: -0.1700

Data Index: 5559386 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2685. Min Act: -0.1700

Data Index: 6989226 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2595. Min Act: -0.1700

Data Index: 2363111 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2319. Min Act: -0.1700

Data Index: 3848977 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2159. Min Act: -0.1700

Data Index: 4423726 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2109. Min Act: -0.1700

Data Index: 5632369 (Open Web Text)

Max Activating Token Index: 225

Text #9

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2208. Min Act: -0.1700

Data Index: 3654605 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1965. Min Act: -0.1700

Data Index: 4743502 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1861. Min Act: -0.1700

Data Index: 532769 (Open Web Text)

Max Activating Token Index: 138

Text #12

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1815. Min Act: -0.1700

Data Index: 2370556 (Open Web Text)

Max Activating Token Index: 290

Text #13

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1928. Min Act: -0.1700

Data Index: 5632367 (Open Web Text)

Max Activating Token Index: 249

Text #14

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.2004. Min Act: -0.1700

Data Index: 6913343 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1822. Min Act: -0.1700

Data Index: 4743504 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1867. Min Act: -0.1700

Data Index: 6741106 (Open Web Text)

Max Activating Token Index: 27

Text #17

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1987. Min Act: -0.1700

Data Index: 2370561 (Open Web Text)

Max Activating Token Index: 85

Text #18

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1935. Min Act: -0.1700

Data Index: 1842712 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 3.3648. Min Range: -3.3648

Max Act: 3.1794. Min Act: -0.1700

Data Index: 3654607 (Open Web Text)

Max Activating Token Index: 477