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

Dataset: Open Web Text

Neuron 1149 in Layer 1

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: 5.5779. Min Range: -5.5779

Max Act: 5.5779. Min Act: -0.1700

Data Index: 7906250 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4943. Min Act: -0.1700

Data Index: 5522797 (Open Web Text)

Max Activating Token Index: 702

Text #2

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5402. Min Act: -0.1700

Data Index: 5928114 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4190. Min Act: -0.1700

Data Index: 8485546 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3943. Min Act: -0.1700

Data Index: 636940 (Open Web Text)

Max Activating Token Index: 524

Text #5

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4101. Min Act: -0.1700

Data Index: 1790031 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3388. Min Act: -0.1700

Data Index: 2034909 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3460. Min Act: -0.1700

Data Index: 6930756 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3452. Min Act: -0.1700

Data Index: 2592292 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3343. Min Act: -0.1700

Data Index: 3990310 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3252. Min Act: -0.1700

Data Index: 2896411 (Open Web Text)

Max Activating Token Index: 867

Text #11

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3660. Min Act: -0.1700

Data Index: 6783399 (Open Web Text)

Max Activating Token Index: 948

Text #12

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3118. Min Act: -0.1700

Data Index: 4294418 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3059. Min Act: -0.1700

Data Index: 4248361 (Open Web Text)

Max Activating Token Index: 610

Text #14

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.2766. Min Act: -0.1700

Data Index: 2608895 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3010. Min Act: -0.1700

Data Index: 2589235 (Open Web Text)

Max Activating Token Index: 45

Text #16

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.2839. Min Act: -0.1700

Data Index: 3565767 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.2879. Min Act: -0.1700

Data Index: 1489895 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.3114. Min Act: -0.1700

Data Index: 2487815 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.2944. Min Act: -0.1700

Data Index: 759496 (Open Web Text)

Max Activating Token Index: 774