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

Dataset: Open Web Text

Neuron 2363 in Layer 3

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: 3.8661. Min Range: -3.8661

Max Act: 3.8488. Min Act: -0.1700

Data Index: 5825069 (Open Web Text)

Max Activating Token Index: 177

Text #1

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8661. Min Act: -0.1700

Data Index: 3005873 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7908. Min Act: -0.1700

Data Index: 8526343 (Open Web Text)

Max Activating Token Index: 587

Text #3

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8154. Min Act: -0.1700

Data Index: 6018939 (Open Web Text)

Max Activating Token Index: 351

Text #4

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7803. Min Act: -0.1700

Data Index: 3321459 (Open Web Text)

Max Activating Token Index: 104

Text #5

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8078. Min Act: -0.1700

Data Index: 8762504 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7572. Min Act: -0.1700

Data Index: 5860209 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7556. Min Act: -0.1700

Data Index: 4291716 (Open Web Text)

Max Activating Token Index: 778

Text #8

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7401. Min Act: -0.1700

Data Index: 1701581 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7537. Min Act: -0.1700

Data Index: 4549778 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7428. Min Act: -0.1700

Data Index: 6012572 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7265. Min Act: -0.1700

Data Index: 4132318 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7491. Min Act: -0.1700

Data Index: 7985679 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7056. Min Act: -0.1700

Data Index: 7721202 (Open Web Text)

Max Activating Token Index: 792

Text #14

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7053. Min Act: -0.1700

Data Index: 6191618 (Open Web Text)

Max Activating Token Index: 120

Text #15

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7047. Min Act: -0.1700

Data Index: 5264911 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7123. Min Act: -0.1700

Data Index: 5149454 (Open Web Text)

Max Activating Token Index: 293

Text #17

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7276. Min Act: -0.1700

Data Index: 4761246 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7417. Min Act: -0.1700

Data Index: 2755720 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7133. Min Act: -0.1700

Data Index: 3370707 (Open Web Text)

Max Activating Token Index: 40