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

Dataset: Open Web Text

Neuron 954 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: 1.8875. Min Range: -1.8875

Max Act: 1.8875. Min Act: -0.1700

Data Index: 6574053 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8815. Min Act: -0.1700

Data Index: 1563519 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8851. Min Act: -0.1700

Data Index: 8147172 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8654. Min Act: -0.1700

Data Index: 373493 (Open Web Text)

Max Activating Token Index: 311

Text #4

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8643. Min Act: -0.1700

Data Index: 7994197 (Open Web Text)

Max Activating Token Index: 538

Text #5

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8604. Min Act: -0.1700

Data Index: 1296585 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8522. Min Act: -0.1700

Data Index: 3717473 (Open Web Text)

Max Activating Token Index: 112

Text #7

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8468. Min Act: -0.1700

Data Index: 4883942 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8442. Min Act: -0.1700

Data Index: 5735124 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8540. Min Act: -0.1700

Data Index: 6508662 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8461. Min Act: -0.1700

Data Index: 4244410 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8410. Min Act: -0.1700

Data Index: 417457 (Open Web Text)

Max Activating Token Index: 214

Text #12

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8470. Min Act: -0.1700

Data Index: 8346763 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8298. Min Act: -0.1700

Data Index: 1711823 (Open Web Text)

Max Activating Token Index: 282

Text #14

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8304. Min Act: -0.1700

Data Index: 1659787 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8330. Min Act: -0.1700

Data Index: 4588328 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8378. Min Act: -0.1700

Data Index: 3532213 (Open Web Text)

Max Activating Token Index: 361

Text #17

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8321. Min Act: -0.1700

Data Index: 4082693 (Open Web Text)

Max Activating Token Index: 155

Text #18

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8257. Min Act: -0.1700

Data Index: 4521785 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8191. Min Act: -0.1700

Data Index: 6455682 (Open Web Text)

Max Activating Token Index: 445