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

Dataset: Open Web Text

Neuron 1468 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: 4.3204. Min Range: -4.3204

Max Act: 4.3204. Min Act: -0.1700

Data Index: 5381915 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.2149. Min Act: -0.1700

Data Index: 1805099 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.1596. Min Act: -0.1700

Data Index: 196461 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.1652. Min Act: -0.1700

Data Index: 4548684 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.1406. Min Act: -0.1700

Data Index: 2072143 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.1143. Min Act: -0.1700

Data Index: 3827749 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.1001. Min Act: -0.1700

Data Index: 4700123 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0964. Min Act: -0.1700

Data Index: 4983331 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0674. Min Act: -0.1700

Data Index: 7074245 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0674. Min Act: -0.1700

Data Index: 6255781 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0721. Min Act: -0.1700

Data Index: 2622407 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0430. Min Act: -0.1700

Data Index: 7968607 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0270. Min Act: -0.1700

Data Index: 787770 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0522. Min Act: -0.1700

Data Index: 1720051 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0309. Min Act: -0.1700

Data Index: 3246472 (Open Web Text)

Max Activating Token Index: 433

Text #15

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0356. Min Act: -0.1700

Data Index: 5055921 (Open Web Text)

Max Activating Token Index: 45

Text #16

Max Range: 4.3204. Min Range: -4.3204

Max Act: 3.9995. Min Act: -0.1700

Data Index: 2916360 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0303. Min Act: -0.1700

Data Index: 2578428 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0064. Min Act: -0.1700

Data Index: 3844385 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.3204. Min Range: -4.3204

Max Act: 4.0129. Min Act: -0.1700

Data Index: 2401770 (Open Web Text)

Max Activating Token Index: 4