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

Dataset: Open Web Text

Neuron 415 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: 3.0875. Min Range: -3.0875

Max Act: 3.0875. Min Act: -0.1700

Data Index: 6154014 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9878. Min Act: -0.1700

Data Index: 2679877 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9944. Min Act: -0.1700

Data Index: 3098815 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9618. Min Act: -0.1700

Data Index: 7230218 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9387. Min Act: -0.1700

Data Index: 7886203 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9487. Min Act: -0.1700

Data Index: 8702597 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9580. Min Act: -0.1700

Data Index: 3827705 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9288. Min Act: -0.1700

Data Index: 1444104 (Open Web Text)

Max Activating Token Index: 375

Text #8

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9241. Min Act: -0.1700

Data Index: 618240 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9329. Min Act: -0.1700

Data Index: 4810089 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9271. Min Act: -0.1700

Data Index: 4421906 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9378. Min Act: -0.1700

Data Index: 4373118 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9205. Min Act: -0.1700

Data Index: 3091067 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9157. Min Act: -0.1700

Data Index: 6919388 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9161. Min Act: -0.1700

Data Index: 5595476 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9233. Min Act: -0.1700

Data Index: 3333769 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9039. Min Act: -0.1700

Data Index: 3199062 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.8988. Min Act: -0.1700

Data Index: 1300444 (Open Web Text)

Max Activating Token Index: 188

Text #18

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9125. Min Act: -0.1700

Data Index: 799387 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.9021. Min Act: -0.1700

Data Index: 7519270 (Open Web Text)

Max Activating Token Index: 114