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

Dataset: Open Web Text

Neuron 1066 in Layer 5

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: 4.5142. Min Range: -4.5142

Max Act: 4.5142. Min Act: -0.1700

Data Index: 6539750 (Open Web Text)

Max Activating Token Index: 604

Text #1

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.4079. Min Act: -0.1700

Data Index: 7379755 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.3341. Min Act: -0.1700

Data Index: 1115891 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.3447. Min Act: -0.1700

Data Index: 4215291 (Open Web Text)

Max Activating Token Index: 283

Text #4

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2878. Min Act: -0.1700

Data Index: 5332275 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2327. Min Act: -0.1700

Data Index: 8497944 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2396. Min Act: -0.1700

Data Index: 8793569 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2448. Min Act: -0.1700

Data Index: 1330266 (Open Web Text)

Max Activating Token Index: 172

Text #8

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2546. Min Act: -0.1700

Data Index: 5317979 (Open Web Text)

Max Activating Token Index: 380

Text #9

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2668. Min Act: -0.1700

Data Index: 2473177 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2502. Min Act: -0.1700

Data Index: 1551434 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2389. Min Act: -0.1700

Data Index: 6337951 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2181. Min Act: -0.1700

Data Index: 4404947 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2431. Min Act: -0.1700

Data Index: 7714789 (Open Web Text)

Max Activating Token Index: 664

Text #14

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2416. Min Act: -0.1700

Data Index: 2339816 (Open Web Text)

Max Activating Token Index: 787

Text #15

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.1922. Min Act: -0.1700

Data Index: 782527 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.1761. Min Act: -0.1700

Data Index: 6394923 (Open Web Text)

Max Activating Token Index: 512

Text #17

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.1789. Min Act: -0.1700

Data Index: 1854107 (Open Web Text)

Max Activating Token Index: 771

Text #18

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2049. Min Act: -0.1700

Data Index: 4612223 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 4.5142. Min Range: -4.5142

Max Act: 4.2045. Min Act: -0.1700

Data Index: 903820 (Open Web Text)

Max Activating Token Index: 77