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

Dataset: Open Web Text

Neuron 484 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: 1.9956. Min Range: -1.9956

Max Act: 1.9956. Min Act: -0.1700

Data Index: 4489249 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.8339. Min Act: -0.1700

Data Index: 1014295 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7841. Min Act: -0.1699

Data Index: 7800083 (Open Web Text)

Max Activating Token Index: 121

Text #3

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7941. Min Act: -0.1700

Data Index: 7733675 (Open Web Text)

Max Activating Token Index: 172

Text #4

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7546. Min Act: -0.1700

Data Index: 1381077 (Open Web Text)

Max Activating Token Index: 146

Text #5

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7516. Min Act: -0.1700

Data Index: 591192 (Open Web Text)

Max Activating Token Index: 690

Text #6

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7719. Min Act: -0.1700

Data Index: 6141137 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7419. Min Act: -0.1700

Data Index: 7895490 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7451. Min Act: -0.1700

Data Index: 4099010 (Open Web Text)

Max Activating Token Index: 692

Text #9

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7485. Min Act: -0.1699

Data Index: 7381313 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7322. Min Act: -0.1700

Data Index: 2103889 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7279. Min Act: -0.1700

Data Index: 6719625 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7327. Min Act: -0.1700

Data Index: 2332087 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7383. Min Act: -0.1700

Data Index: 7835120 (Open Web Text)

Max Activating Token Index: 699

Text #14

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7200. Min Act: -0.1700

Data Index: 2283487 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7312. Min Act: -0.1700

Data Index: 7440243 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7090. Min Act: -0.1700

Data Index: 4514095 (Open Web Text)

Max Activating Token Index: 519

Text #17

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7085. Min Act: -0.1700

Data Index: 5379661 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7065. Min Act: -0.1700

Data Index: 6681515 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7108. Min Act: -0.1698

Data Index: 1585433 (Open Web Text)

Max Activating Token Index: 116