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

Dataset: Open Web Text

Neuron 3037 in Layer 2

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: 0.9403. Min Range: -0.9403

Max Act: 0.9403. Min Act: -0.1700

Data Index: 7953622 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.9212. Min Act: -0.1698

Data Index: 8645278 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.9195. Min Act: -0.1700

Data Index: 8183694 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.9094. Min Act: -0.1700

Data Index: 7098508 (Open Web Text)

Max Activating Token Index: 729

Text #4

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.9199. Min Act: -0.1700

Data Index: 5784822 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.9029. Min Act: -0.1700

Data Index: 1002474 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8805. Min Act: -0.1700

Data Index: 617267 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8704. Min Act: -0.1700

Data Index: 3656045 (Open Web Text)

Max Activating Token Index: 90

Text #8

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8645. Min Act: -0.1700

Data Index: 202288 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8637. Min Act: -0.1700

Data Index: 2725678 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8808. Min Act: -0.1695

Data Index: 2725677 (Open Web Text)

Max Activating Token Index: 716

Text #11

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8619. Min Act: -0.1700

Data Index: 2538747 (Open Web Text)

Max Activating Token Index: 275

Text #12

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8593. Min Act: -0.1700

Data Index: 4755740 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8524. Min Act: -0.1700

Data Index: 7612987 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8472. Min Act: -0.1700

Data Index: 3678150 (Open Web Text)

Max Activating Token Index: 973

Text #15

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8450. Min Act: -0.1700

Data Index: 3727695 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8418. Min Act: -0.1700

Data Index: 7790552 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8537. Min Act: -0.1700

Data Index: 183022 (Open Web Text)

Max Activating Token Index: 242

Text #18

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8254. Min Act: -0.1700

Data Index: 2499860 (Open Web Text)

Max Activating Token Index: 814

Text #19

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8357. Min Act: -0.1696

Data Index: 423219 (Open Web Text)

Max Activating Token Index: 882