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

Dataset: Open Web Text

Neuron 2662 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: 0.7592. Min Range: -0.7592

Max Act: 0.7592. Min Act: -0.1699

Data Index: 6461655 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7291. Min Act: -0.1700

Data Index: 6310356 (Open Web Text)

Max Activating Token Index: 326

Text #2

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7516. Min Act: -0.1700

Data Index: 130249 (Open Web Text)

Max Activating Token Index: 316

Text #3

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7347. Min Act: -0.1700

Data Index: 1077323 (Open Web Text)

Max Activating Token Index: 311

Text #4

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7204. Min Act: -0.1700

Data Index: 7331058 (Open Web Text)

Max Activating Token Index: 309

Text #5

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7142. Min Act: -0.1700

Data Index: 4452553 (Open Web Text)

Max Activating Token Index: 319

Text #6

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7194. Min Act: -0.1700

Data Index: 539792 (Open Web Text)

Max Activating Token Index: 49

Text #7

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6941. Min Act: -0.1700

Data Index: 7441358 (Open Web Text)

Max Activating Token Index: 311

Text #8

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7119. Min Act: -0.1700

Data Index: 5044429 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7113. Min Act: -0.1700

Data Index: 5276979 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7067. Min Act: -0.1700

Data Index: 3293061 (Open Web Text)

Max Activating Token Index: 308

Text #11

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7041. Min Act: -0.1700

Data Index: 942336 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6948. Min Act: -0.1700

Data Index: 6208491 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6877. Min Act: -0.1700

Data Index: 3685302 (Open Web Text)

Max Activating Token Index: 327

Text #14

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7058. Min Act: -0.1700

Data Index: 5642687 (Open Web Text)

Max Activating Token Index: 37

Text #15

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6987. Min Act: -0.1700

Data Index: 1380006 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7007. Min Act: -0.1700

Data Index: 5036469 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7020. Min Act: -0.1700

Data Index: 2654874 (Open Web Text)

Max Activating Token Index: 308

Text #18

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6967. Min Act: -0.1700

Data Index: 3522356 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7005. Min Act: -0.1700

Data Index: 5762429 (Open Web Text)

Max Activating Token Index: 280