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

Dataset: Open Web Text

Neuron 839 in Layer 1

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: 1.9283. Min Range: -1.9283

Max Act: 1.9283. Min Act: -0.1700

Data Index: 4026651 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.9191. Min Act: -0.1700

Data Index: 6418742 (Open Web Text)

Max Activating Token Index: 146

Text #2

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.9206. Min Act: -0.1700

Data Index: 7610539 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.9030. Min Act: -0.1700

Data Index: 1786743 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.9133. Min Act: -0.1700

Data Index: 7089926 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8835. Min Act: -0.1700

Data Index: 4635349 (Open Web Text)

Max Activating Token Index: 413

Text #6

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8908. Min Act: -0.1700

Data Index: 6849070 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8835. Min Act: -0.1700

Data Index: 2432142 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8676. Min Act: -0.1700

Data Index: 91998 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8720. Min Act: -0.1700

Data Index: 6008958 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8644. Min Act: -0.1700

Data Index: 2034605 (Open Web Text)

Max Activating Token Index: 892

Text #11

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8748. Min Act: -0.1700

Data Index: 1427196 (Open Web Text)

Max Activating Token Index: 437

Text #12

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8628. Min Act: -0.1700

Data Index: 1435981 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8803. Min Act: -0.1700

Data Index: 2398325 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8665. Min Act: -0.1700

Data Index: 5715748 (Open Web Text)

Max Activating Token Index: 378

Text #15

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8769. Min Act: -0.1700

Data Index: 5390917 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8679. Min Act: -0.1700

Data Index: 4737446 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8533. Min Act: -0.1700

Data Index: 1184878 (Open Web Text)

Max Activating Token Index: 502

Text #18

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8572. Min Act: -0.1699

Data Index: 2377323 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8685. Min Act: -0.1700

Data Index: 2037057 (Open Web Text)

Max Activating Token Index: 7