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

Dataset: Open Web Text

Neuron 136 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: 1.6672. Min Range: -1.6672

Max Act: 1.6655. Min Act: -0.1700

Data Index: 5137377 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.6672. Min Act: -0.1700

Data Index: 5617582 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.6265. Min Act: -0.1675

Data Index: 6402437 (Open Web Text)

Max Activating Token Index: 426

Text #3

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.6059. Min Act: -0.1700

Data Index: 7633253 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5954. Min Act: -0.1700

Data Index: 3246464 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.6011. Min Act: -0.1699

Data Index: 1983561 (Open Web Text)

Max Activating Token Index: 145

Text #6

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5772. Min Act: -0.1700

Data Index: 7346058 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5854. Min Act: -0.1700

Data Index: 784703 (Open Web Text)

Max Activating Token Index: 186

Text #8

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5799. Min Act: -0.1700

Data Index: 4876740 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5640. Min Act: -0.1700

Data Index: 1299050 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5693. Min Act: -0.1700

Data Index: 3938755 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5690. Min Act: -0.1700

Data Index: 8375575 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5744. Min Act: -0.1700

Data Index: 948794 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5696. Min Act: -0.1699

Data Index: 5432048 (Open Web Text)

Max Activating Token Index: 35

Text #14

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5711. Min Act: -0.1700

Data Index: 5444447 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5635. Min Act: -0.1700

Data Index: 686827 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5613. Min Act: -0.1700

Data Index: 2744450 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5659. Min Act: -0.1700

Data Index: 6669959 (Open Web Text)

Max Activating Token Index: 975

Text #18

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5574. Min Act: -0.1700

Data Index: 6447705 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.5545. Min Act: -0.1700

Data Index: 2577583 (Open Web Text)

Max Activating Token Index: 88