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

Dataset: Open Web Text

Neuron 44 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: 3.6254. Min Range: -3.6254

Max Act: 3.6254. Min Act: -0.1700

Data Index: 4585506 (Open Web Text)

Max Activating Token Index: 670

Text #1

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.5433. Min Act: -0.1700

Data Index: 6627286 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.5400. Min Act: -0.1700

Data Index: 6340860 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4473. Min Act: -0.1700

Data Index: 3865126 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4545. Min Act: -0.1700

Data Index: 5541214 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4405. Min Act: -0.1700

Data Index: 7527511 (Open Web Text)

Max Activating Token Index: 119

Text #6

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4494. Min Act: -0.1700

Data Index: 1877810 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4482. Min Act: -0.1700

Data Index: 3615275 (Open Web Text)

Max Activating Token Index: 264

Text #8

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4344. Min Act: -0.1700

Data Index: 4974307 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4389. Min Act: -0.1700

Data Index: 8790870 (Open Web Text)

Max Activating Token Index: 55

Text #10

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4212. Min Act: -0.1700

Data Index: 3503884 (Open Web Text)

Max Activating Token Index: 123

Text #11

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4145. Min Act: -0.1700

Data Index: 7571310 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4127. Min Act: -0.1700

Data Index: 497669 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4156. Min Act: -0.1700

Data Index: 3279736 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.3941. Min Act: -0.1700

Data Index: 4638347 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.4023. Min Act: -0.1700

Data Index: 5622128 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.3583. Min Act: -0.1700

Data Index: 3606884 (Open Web Text)

Max Activating Token Index: 131

Text #17

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.3948. Min Act: -0.1700

Data Index: 3372778 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.3921. Min Act: -0.1700

Data Index: 5547846 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 3.6254. Min Range: -3.6254

Max Act: 3.3742. Min Act: -0.1700

Data Index: 1979636 (Open Web Text)

Max Activating Token Index: 445