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

Dataset: Open Web Text

Neuron 604 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: 4.5047. Min Range: -4.5047

Max Act: 4.5047. Min Act: -0.1700

Data Index: 6366573 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.3240. Min Act: -0.1700

Data Index: 6489317 (Open Web Text)

Max Activating Token Index: 737

Text #2

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2998. Min Act: -0.1700

Data Index: 3342049 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2880. Min Act: -0.1700

Data Index: 1968189 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2537. Min Act: -0.1700

Data Index: 315689 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2547. Min Act: -0.1700

Data Index: 17522 (Open Web Text)

Max Activating Token Index: 1005

Text #6

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2775. Min Act: -0.1700

Data Index: 1955352 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2590. Min Act: -0.1700

Data Index: 3466016 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2589. Min Act: -0.1700

Data Index: 5400243 (Open Web Text)

Max Activating Token Index: 892

Text #9

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2402. Min Act: -0.1700

Data Index: 6127070 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2460. Min Act: -0.1700

Data Index: 4219942 (Open Web Text)

Max Activating Token Index: 138

Text #11

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2707. Min Act: -0.1700

Data Index: 7727085 (Open Web Text)

Max Activating Token Index: 938

Text #12

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2086. Min Act: -0.1700

Data Index: 6884896 (Open Web Text)

Max Activating Token Index: 295

Text #13

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2663. Min Act: -0.1700

Data Index: 2180971 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2177. Min Act: -0.1700

Data Index: 4884246 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2040. Min Act: -0.1700

Data Index: 2282670 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.2147. Min Act: -0.1700

Data Index: 5257238 (Open Web Text)

Max Activating Token Index: 854

Text #17

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.1662. Min Act: -0.1700

Data Index: 628745 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.1491. Min Act: -0.1700

Data Index: 3943121 (Open Web Text)

Max Activating Token Index: 441

Text #19

Max Range: 4.5047. Min Range: -4.5047

Max Act: 4.1686. Min Act: -0.1700

Data Index: 2797795 (Open Web Text)

Max Activating Token Index: 147