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

Dataset: Open Web Text

Neuron 3002 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: 3.1262. Min Range: -3.1262

Max Act: 3.1262. Min Act: -0.1700

Data Index: 2390617 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0891. Min Act: -0.1700

Data Index: 516846 (Open Web Text)

Max Activating Token Index: 331

Text #2

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0739. Min Act: -0.1700

Data Index: 6624118 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0780. Min Act: -0.1700

Data Index: 31800 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0488. Min Act: -0.1700

Data Index: 2211239 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0530. Min Act: -0.1700

Data Index: 3533398 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0601. Min Act: -0.1700

Data Index: 483209 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0459. Min Act: -0.1700

Data Index: 6749131 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0497. Min Act: -0.1700

Data Index: 1181285 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0207. Min Act: -0.1700

Data Index: 7475286 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0158. Min Act: -0.1700

Data Index: 5197934 (Open Web Text)

Max Activating Token Index: 391

Text #11

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0299. Min Act: -0.1700

Data Index: 2802308 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0056. Min Act: -0.1700

Data Index: 2813350 (Open Web Text)

Max Activating Token Index: 990

Text #13

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0134. Min Act: -0.1700

Data Index: 3896565 (Open Web Text)

Max Activating Token Index: 61

Text #14

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0113. Min Act: -0.1700

Data Index: 4806870 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0031. Min Act: -0.1700

Data Index: 6801985 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0174. Min Act: -0.1700

Data Index: 4543342 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0093. Min Act: -0.1700

Data Index: 2023319 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 3.1262. Min Range: -3.1262

Max Act: 2.9873. Min Act: -0.1700

Data Index: 1336800 (Open Web Text)

Max Activating Token Index: 420

Text #19

Max Range: 3.1262. Min Range: -3.1262

Max Act: 2.9914. Min Act: -0.1700

Data Index: 3903631 (Open Web Text)

Max Activating Token Index: 271