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

Dataset: Open Web Text

Neuron 803 in Layer 6

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: 3.1950. Min Range: -3.1950

Max Act: 3.1779. Min Act: -0.1700

Data Index: 3996362 (Open Web Text)

Max Activating Token Index: 1007

Text #1

Max Range: 3.1950. Min Range: -3.1950

Max Act: 3.1950. Min Act: -0.1700

Data Index: 6637716 (Open Web Text)

Max Activating Token Index: 700

Text #2

Max Range: 3.1950. Min Range: -3.1950

Max Act: 3.1229. Min Act: -0.1700

Data Index: 23965 (Open Web Text)

Max Activating Token Index: 131

Text #3

Max Range: 3.1950. Min Range: -3.1950

Max Act: 3.0643. Min Act: -0.1700

Data Index: 1723434 (Open Web Text)

Max Activating Token Index: 554

Text #4

Max Range: 3.1950. Min Range: -3.1950

Max Act: 3.0631. Min Act: -0.1700

Data Index: 1392947 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 3.1950. Min Range: -3.1950

Max Act: 3.0391. Min Act: -0.1700

Data Index: 6397171 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9860. Min Act: -0.1700

Data Index: 2814827 (Open Web Text)

Max Activating Token Index: 207

Text #7

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9819. Min Act: -0.1700

Data Index: 7690015 (Open Web Text)

Max Activating Token Index: 838

Text #8

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9965. Min Act: -0.1700

Data Index: 4417208 (Open Web Text)

Max Activating Token Index: 441

Text #9

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9947. Min Act: -0.1700

Data Index: 4187466 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9802. Min Act: -0.1700

Data Index: 6462468 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9835. Min Act: -0.1700

Data Index: 6605854 (Open Web Text)

Max Activating Token Index: 751

Text #12

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9856. Min Act: -0.1700

Data Index: 3996363 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9521. Min Act: -0.1700

Data Index: 3792039 (Open Web Text)

Max Activating Token Index: 520

Text #14

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9419. Min Act: -0.1700

Data Index: 3268704 (Open Web Text)

Max Activating Token Index: 457

Text #15

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9328. Min Act: -0.1700

Data Index: 1726575 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9033. Min Act: -0.1700

Data Index: 4814383 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9335. Min Act: -0.1700

Data Index: 7420925 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9354. Min Act: -0.1700

Data Index: 1664084 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 3.1950. Min Range: -3.1950

Max Act: 2.9149. Min Act: -0.1700

Data Index: 7162554 (Open Web Text)

Max Activating Token Index: 137