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

Dataset: Open Web Text

Neuron 2856 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: 3.3357. Min Range: -3.3357

Max Act: 3.3357. Min Act: -0.1700

Data Index: 541759 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.3043. Min Act: -0.1700

Data Index: 1102399 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.3077. Min Act: -0.1700

Data Index: 7878768 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2656. Min Act: -0.1700

Data Index: 3716994 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2732. Min Act: -0.1700

Data Index: 3473655 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2548. Min Act: -0.1700

Data Index: 8649757 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2612. Min Act: -0.1700

Data Index: 5747187 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2478. Min Act: -0.1700

Data Index: 6178652 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2406. Min Act: -0.1700

Data Index: 7144138 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2425. Min Act: -0.1700

Data Index: 6222728 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2530. Min Act: -0.1700

Data Index: 5749442 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2254. Min Act: -0.1700

Data Index: 3484597 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2278. Min Act: -0.1700

Data Index: 2125223 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2347. Min Act: -0.1700

Data Index: 4806887 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.1944. Min Act: -0.1700

Data Index: 3832133 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2166. Min Act: -0.1700

Data Index: 528002 (Open Web Text)

Max Activating Token Index: 23

Text #16

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.1924. Min Act: -0.1700

Data Index: 6161998 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2042. Min Act: -0.1700

Data Index: 2650895 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.2104. Min Act: -0.1700

Data Index: 5457832 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3357. Min Range: -3.3357

Max Act: 3.1926. Min Act: -0.1700

Data Index: 841726 (Open Web Text)

Max Activating Token Index: 81