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

Dataset: Open Web Text

Neuron 3046 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: 3.9921. Min Range: -3.9921

Max Act: 3.9921. Min Act: -0.1700

Data Index: 5859044 (Open Web Text)

Max Activating Token Index: 474

Text #1

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.9576. Min Act: -0.1700

Data Index: 1935889 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.9722. Min Act: -0.1700

Data Index: 909842 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.9877. Min Act: -0.1700

Data Index: 2128301 (Open Web Text)

Max Activating Token Index: 785

Text #4

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.9878. Min Act: -0.1700

Data Index: 2667959 (Open Web Text)

Max Activating Token Index: 974

Text #5

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.9317. Min Act: -0.1700

Data Index: 2771321 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8811. Min Act: -0.1700

Data Index: 6128467 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8907. Min Act: -0.1700

Data Index: 6691506 (Open Web Text)

Max Activating Token Index: 235

Text #8

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8970. Min Act: -0.1700

Data Index: 4983177 (Open Web Text)

Max Activating Token Index: 810

Text #9

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.9096. Min Act: -0.1700

Data Index: 4850645 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8955. Min Act: -0.1700

Data Index: 4623525 (Open Web Text)

Max Activating Token Index: 28

Text #11

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8707. Min Act: -0.1700

Data Index: 2226667 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8744. Min Act: -0.1700

Data Index: 6148426 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8538. Min Act: -0.1700

Data Index: 8348561 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8639. Min Act: -0.1699

Data Index: 2618371 (Open Web Text)

Max Activating Token Index: 1003

Text #15

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8565. Min Act: -0.1700

Data Index: 8522383 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8695. Min Act: -0.1700

Data Index: 672284 (Open Web Text)

Max Activating Token Index: 316

Text #17

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8562. Min Act: -0.1700

Data Index: 235830 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8698. Min Act: -0.1700

Data Index: 2440669 (Open Web Text)

Max Activating Token Index: 697

Text #19

Max Range: 3.9921. Min Range: -3.9921

Max Act: 3.8450. Min Act: -0.1700

Data Index: 7183191 (Open Web Text)

Max Activating Token Index: 547