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

Dataset: Open Web Text

Neuron 2113 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: 2.8491. Min Range: -2.8491

Max Act: 2.8491. Min Act: -0.1700

Data Index: 3912239 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.8271. Min Act: -0.1700

Data Index: 4216108 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.8090. Min Act: -0.1700

Data Index: 6250137 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.8052. Min Act: -0.1700

Data Index: 2101841 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7840. Min Act: -0.1700

Data Index: 452010 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7931. Min Act: -0.1700

Data Index: 1199277 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7747. Min Act: -0.1700

Data Index: 2768399 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7579. Min Act: -0.1700

Data Index: 8214974 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7612. Min Act: -0.1700

Data Index: 3405103 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7531. Min Act: -0.1700

Data Index: 8439274 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7330. Min Act: -0.1700

Data Index: 7976761 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7345. Min Act: -0.1700

Data Index: 2189481 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7291. Min Act: -0.1700

Data Index: 4715773 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7245. Min Act: -0.1700

Data Index: 6605985 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7295. Min Act: -0.1700

Data Index: 3968217 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7260. Min Act: -0.1700

Data Index: 3056747 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7284. Min Act: -0.1700

Data Index: 4687221 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7248. Min Act: -0.1700

Data Index: 8296863 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7147. Min Act: -0.1700

Data Index: 3533175 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.8491. Min Range: -2.8491

Max Act: 2.7114. Min Act: -0.1700

Data Index: 2630143 (Open Web Text)

Max Activating Token Index: 6