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

Dataset: Open Web Text

Neuron 2100 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: 4.2622. Min Range: -4.2622

Max Act: 4.2622. Min Act: -0.1700

Data Index: 6478769 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.2622. Min Range: -4.2622

Max Act: 4.0607. Min Act: -0.1700

Data Index: 3120853 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 4.2622. Min Range: -4.2622

Max Act: 4.0397. Min Act: -0.1700

Data Index: 6034552 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 4.2622. Min Range: -4.2622

Max Act: 4.0188. Min Act: -0.1700

Data Index: 6189362 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 4.2622. Min Range: -4.2622

Max Act: 4.0120. Min Act: -0.1700

Data Index: 2361904 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 4.2622. Min Range: -4.2622

Max Act: 4.0109. Min Act: -0.1700

Data Index: 1472868 (Open Web Text)

Max Activating Token Index: 54

Text #6

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9793. Min Act: -0.1700

Data Index: 6492205 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9740. Min Act: -0.1700

Data Index: 3687986 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9870. Min Act: -0.1700

Data Index: 2221747 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9666. Min Act: -0.1700

Data Index: 8535269 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9661. Min Act: -0.1700

Data Index: 439472 (Open Web Text)

Max Activating Token Index: 93

Text #11

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9603. Min Act: -0.1700

Data Index: 5201616 (Open Web Text)

Max Activating Token Index: 119

Text #12

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9663. Min Act: -0.1700

Data Index: 3275135 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9623. Min Act: -0.1700

Data Index: 2528371 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9610. Min Act: -0.1700

Data Index: 6125967 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9451. Min Act: -0.1700

Data Index: 4868137 (Open Web Text)

Max Activating Token Index: 76

Text #16

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9443. Min Act: -0.1700

Data Index: 5948453 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9315. Min Act: -0.1700

Data Index: 2285477 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.8946. Min Act: -0.1700

Data Index: 5205376 (Open Web Text)

Max Activating Token Index: 96

Text #19

Max Range: 4.2622. Min Range: -4.2622

Max Act: 3.9237. Min Act: -0.1700

Data Index: 7130482 (Open Web Text)

Max Activating Token Index: 37