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

Dataset: Open Web Text

Neuron 700 in Layer 0

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: 1.6367. Min Range: -1.6367

Max Act: 1.6367. Min Act: -0.1663

Data Index: 5626490 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6263. Min Act: -0.1663

Data Index: 4539038 (Open Web Text)

Max Activating Token Index: 185

Text #2

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6048. Min Act: -0.1663

Data Index: 5009909 (Open Web Text)

Max Activating Token Index: 565

Text #3

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6022. Min Act: -0.1663

Data Index: 3099506 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6000. Min Act: -0.1688

Data Index: 6010759 (Open Web Text)

Max Activating Token Index: 198

Text #5

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6025. Min Act: -0.1700

Data Index: 3058869 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5914. Min Act: -0.1663

Data Index: 2524063 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5885. Min Act: -0.1663

Data Index: 2891699 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5958. Min Act: -0.1663

Data Index: 4519890 (Open Web Text)

Max Activating Token Index: 167

Text #9

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5982. Min Act: -0.1663

Data Index: 2807244 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5851. Min Act: -0.1663

Data Index: 8068068 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5918. Min Act: -0.1663

Data Index: 5835314 (Open Web Text)

Max Activating Token Index: 211

Text #12

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5811. Min Act: -0.1678

Data Index: 1173780 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5781. Min Act: -0.1663

Data Index: 1705443 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5778. Min Act: -0.1663

Data Index: 4517494 (Open Web Text)

Max Activating Token Index: 80

Text #15

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5733. Min Act: -0.1663

Data Index: 2589966 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5694. Min Act: -0.1663

Data Index: 1131763 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5737. Min Act: -0.1672

Data Index: 4472226 (Open Web Text)

Max Activating Token Index: 44

Text #18

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5741. Min Act: -0.1673

Data Index: 2827415 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5713. Min Act: -0.1663

Data Index: 1900314 (Open Web Text)

Max Activating Token Index: 685