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

Dataset: Open Web Text

Neuron 2215 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: 3.3337. Min Range: -3.3337

Max Act: 3.3337. Min Act: -0.1700

Data Index: 4391386 (Open Web Text)

Max Activating Token Index: 247

Text #1

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.2201. Min Act: -0.1700

Data Index: 2538624 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1728. Min Act: -0.1700

Data Index: 499856 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1450. Min Act: -0.1700

Data Index: 8671923 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1781. Min Act: -0.1700

Data Index: 684710 (Open Web Text)

Max Activating Token Index: 430

Text #5

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1091. Min Act: -0.1700

Data Index: 1529942 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1254. Min Act: -0.1700

Data Index: 8727215 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1129. Min Act: -0.1700

Data Index: 5702264 (Open Web Text)

Max Activating Token Index: 67

Text #8

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1177. Min Act: -0.1700

Data Index: 3385106 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1377. Min Act: -0.1700

Data Index: 3843034 (Open Web Text)

Max Activating Token Index: 500

Text #10

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0948. Min Act: -0.1700

Data Index: 5687306 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1484. Min Act: -0.1700

Data Index: 7219436 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0898. Min Act: -0.1700

Data Index: 2043047 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0947. Min Act: -0.1700

Data Index: 5016272 (Open Web Text)

Max Activating Token Index: 541

Text #14

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0980. Min Act: -0.1700

Data Index: 1525305 (Open Web Text)

Max Activating Token Index: 475

Text #15

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0922. Min Act: -0.1700

Data Index: 6942290 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1229. Min Act: -0.1700

Data Index: 4158762 (Open Web Text)

Max Activating Token Index: 719

Text #17

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0716. Min Act: -0.1700

Data Index: 1250515 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0779. Min Act: -0.1700

Data Index: 3130464 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0726. Min Act: -0.1700

Data Index: 28505 (Open Web Text)

Max Activating Token Index: 417