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

Dataset: Open Web Text

Neuron 914 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: 3.2449. Min Range: -3.2449

Max Act: 3.2449. Min Act: -0.1700

Data Index: 7892447 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0572. Min Act: -0.1700

Data Index: 1410864 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0175. Min Act: -0.1700

Data Index: 2150364 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.9441. Min Act: -0.1700

Data Index: 6792415 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.9356. Min Act: -0.1700

Data Index: 5100325 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.9213. Min Act: -0.1700

Data Index: 8542580 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.9148. Min Act: -0.1700

Data Index: 7645407 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8830. Min Act: -0.1700

Data Index: 5902008 (Open Web Text)

Max Activating Token Index: 95

Text #8

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8697. Min Act: -0.1700

Data Index: 8093640 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8653. Min Act: -0.1700

Data Index: 4220360 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8411. Min Act: -0.1700

Data Index: 7201652 (Open Web Text)

Max Activating Token Index: 730

Text #11

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8451. Min Act: -0.1700

Data Index: 149515 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8114. Min Act: -0.1700

Data Index: 7817305 (Open Web Text)

Max Activating Token Index: 911

Text #13

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8413. Min Act: -0.1700

Data Index: 3654339 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8018. Min Act: -0.1700

Data Index: 5197900 (Open Web Text)

Max Activating Token Index: 365

Text #15

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.7701. Min Act: -0.1700

Data Index: 7607184 (Open Web Text)

Max Activating Token Index: 966

Text #16

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8021. Min Act: -0.1700

Data Index: 629350 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.7978. Min Act: -0.1700

Data Index: 3400095 (Open Web Text)

Max Activating Token Index: 668

Text #18

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8278. Min Act: -0.1700

Data Index: 2342300 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 3.2449. Min Range: -3.2449

Max Act: 2.8100. Min Act: -0.1700

Data Index: 8132948 (Open Web Text)

Max Activating Token Index: 672