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

Dataset: Open Web Text

Neuron 2159 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: 2.9161. Min Range: -2.9161

Max Act: 2.8974. Min Act: -0.1700

Data Index: 2806575 (Open Web Text)

Max Activating Token Index: 956

Text #1

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.9106. Min Act: -0.1700

Data Index: 6343473 (Open Web Text)

Max Activating Token Index: 791

Text #2

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.9161. Min Act: -0.1700

Data Index: 2729679 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8938. Min Act: -0.1700

Data Index: 6704980 (Open Web Text)

Max Activating Token Index: 253

Text #4

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8914. Min Act: -0.1700

Data Index: 6138688 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.9024. Min Act: -0.1700

Data Index: 6293206 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.9015. Min Act: -0.1700

Data Index: 3681087 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8920. Min Act: -0.1700

Data Index: 8653543 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8986. Min Act: -0.1700

Data Index: 4385111 (Open Web Text)

Max Activating Token Index: 319

Text #9

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.9015. Min Act: -0.1700

Data Index: 2791227 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8898. Min Act: -0.1700

Data Index: 6666508 (Open Web Text)

Max Activating Token Index: 756

Text #11

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8607. Min Act: -0.1700

Data Index: 8247303 (Open Web Text)

Max Activating Token Index: 632

Text #12

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8827. Min Act: -0.1700

Data Index: 7133261 (Open Web Text)

Max Activating Token Index: 979

Text #13

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8742. Min Act: -0.1700

Data Index: 2032687 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8649. Min Act: -0.1700

Data Index: 5228409 (Open Web Text)

Max Activating Token Index: 358

Text #15

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8472. Min Act: -0.1700

Data Index: 2723272 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8528. Min Act: -0.1700

Data Index: 4671343 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8453. Min Act: -0.1700

Data Index: 5013875 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8553. Min Act: -0.1700

Data Index: 6428030 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.9161. Min Range: -2.9161

Max Act: 2.8590. Min Act: -0.1700

Data Index: 7539794 (Open Web Text)

Max Activating Token Index: 27