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

Dataset: Open Web Text

Neuron 1814 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: 4.6024. Min Range: -4.6024

Max Act: 4.6024. Min Act: -0.1700

Data Index: 482721 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.5099. Min Act: -0.1700

Data Index: 1288735 (Open Web Text)

Max Activating Token Index: 796

Text #2

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.5001. Min Act: -0.1700

Data Index: 6905174 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.4643. Min Act: -0.1700

Data Index: 2441561 (Open Web Text)

Max Activating Token Index: 873

Text #4

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.4177. Min Act: -0.1700

Data Index: 6402131 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3888. Min Act: -0.1700

Data Index: 8088485 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3960. Min Act: -0.1700

Data Index: 8236000 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3940. Min Act: -0.1700

Data Index: 1173265 (Open Web Text)

Max Activating Token Index: 365

Text #8

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.4185. Min Act: -0.1700

Data Index: 1336022 (Open Web Text)

Max Activating Token Index: 1012

Text #9

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3920. Min Act: -0.1700

Data Index: 5523469 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.4211. Min Act: -0.1700

Data Index: 7934432 (Open Web Text)

Max Activating Token Index: 977

Text #11

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3845. Min Act: -0.1700

Data Index: 6905175 (Open Web Text)

Max Activating Token Index: 987

Text #12

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.4083. Min Act: -0.1700

Data Index: 6416603 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.4142. Min Act: -0.1700

Data Index: 2190483 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3628. Min Act: -0.1700

Data Index: 1050068 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3660. Min Act: -0.1700

Data Index: 5943291 (Open Web Text)

Max Activating Token Index: 723

Text #16

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3849. Min Act: -0.1700

Data Index: 459975 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3859. Min Act: -0.1700

Data Index: 1962374 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3599. Min Act: -0.1700

Data Index: 310651 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 4.6024. Min Range: -4.6024

Max Act: 4.3640. Min Act: -0.1700

Data Index: 248575 (Open Web Text)

Max Activating Token Index: 944