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

Dataset: Open Web Text

Neuron 113 in Layer 3

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: 3.4368. Min Range: -3.4368

Max Act: 3.4368. Min Act: -0.1700

Data Index: 2028966 (Open Web Text)

Max Activating Token Index: 852

Text #1

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.4246. Min Act: -0.1700

Data Index: 4442355 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.4058. Min Act: -0.1700

Data Index: 8585201 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3898. Min Act: -0.1700

Data Index: 8242601 (Open Web Text)

Max Activating Token Index: 680

Text #4

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3922. Min Act: -0.1700

Data Index: 3323119 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3665. Min Act: -0.1700

Data Index: 6510215 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3413. Min Act: -0.1700

Data Index: 2485479 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3065. Min Act: -0.1700

Data Index: 8008914 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3168. Min Act: -0.1700

Data Index: 5155772 (Open Web Text)

Max Activating Token Index: 421

Text #9

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3021. Min Act: -0.1700

Data Index: 534407 (Open Web Text)

Max Activating Token Index: 840

Text #10

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.3181. Min Act: -0.1700

Data Index: 6543481 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2963. Min Act: -0.1700

Data Index: 7320392 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2805. Min Act: -0.1700

Data Index: 1700696 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2738. Min Act: -0.1700

Data Index: 8548621 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2579. Min Act: -0.1700

Data Index: 5652187 (Open Web Text)

Max Activating Token Index: 221

Text #15

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2428. Min Act: -0.1700

Data Index: 6231258 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2574. Min Act: -0.1700

Data Index: 2500553 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2361. Min Act: -0.1700

Data Index: 259883 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2169. Min Act: -0.1700

Data Index: 5431060 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 3.4368. Min Range: -3.4368

Max Act: 3.2013. Min Act: -0.1700

Data Index: 8496169 (Open Web Text)

Max Activating Token Index: 376