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

Dataset: Open Web Text

Neuron 618 in Layer 4

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: 3.0707. Min Range: -3.0707

Max Act: 3.0707. Min Act: -0.1700

Data Index: 7419065 (Open Web Text)

Max Activating Token Index: 822

Text #1

Max Range: 3.0707. Min Range: -3.0707

Max Act: 3.0186. Min Act: -0.1700

Data Index: 219742 (Open Web Text)

Max Activating Token Index: 397

Text #2

Max Range: 3.0707. Min Range: -3.0707

Max Act: 3.0023. Min Act: -0.1700

Data Index: 77958 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9748. Min Act: -0.1700

Data Index: 2108491 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9927. Min Act: -0.1700

Data Index: 3252435 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9714. Min Act: -0.1700

Data Index: 5294583 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9841. Min Act: -0.1700

Data Index: 3084892 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9922. Min Act: -0.1700

Data Index: 4996169 (Open Web Text)

Max Activating Token Index: 965

Text #8

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9445. Min Act: -0.1700

Data Index: 2656746 (Open Web Text)

Max Activating Token Index: 315

Text #9

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9544. Min Act: -0.1700

Data Index: 1869773 (Open Web Text)

Max Activating Token Index: 917

Text #10

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9600. Min Act: -0.1700

Data Index: 3647927 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9626. Min Act: -0.1700

Data Index: 4159367 (Open Web Text)

Max Activating Token Index: 672

Text #12

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9777. Min Act: -0.1700

Data Index: 6808360 (Open Web Text)

Max Activating Token Index: 765

Text #13

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9389. Min Act: -0.1700

Data Index: 2409806 (Open Web Text)

Max Activating Token Index: 383

Text #14

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.8944. Min Act: -0.1700

Data Index: 7888813 (Open Web Text)

Max Activating Token Index: 862

Text #15

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9400. Min Act: -0.1700

Data Index: 8530445 (Open Web Text)

Max Activating Token Index: 784

Text #16

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9103. Min Act: -0.1700

Data Index: 2496835 (Open Web Text)

Max Activating Token Index: 235

Text #17

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9091. Min Act: -0.1700

Data Index: 360277 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9115. Min Act: -0.1700

Data Index: 5337284 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.9243. Min Act: -0.1700

Data Index: 2916706 (Open Web Text)

Max Activating Token Index: 502