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

Dataset: Open Web Text

Neuron 2445 in Layer 6

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: 4.0349. Min Range: -4.0349

Max Act: 4.0349. Min Act: -0.1700

Data Index: 5065756 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.9611. Min Act: -0.1700

Data Index: 2509868 (Open Web Text)

Max Activating Token Index: 621

Text #2

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.9645. Min Act: -0.1700

Data Index: 48262 (Open Web Text)

Max Activating Token Index: 523

Text #3

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.9037. Min Act: -0.1700

Data Index: 2031266 (Open Web Text)

Max Activating Token Index: 197

Text #4

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.9117. Min Act: -0.1700

Data Index: 3339169 (Open Web Text)

Max Activating Token Index: 115

Text #5

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8665. Min Act: -0.1700

Data Index: 1839903 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8504. Min Act: -0.1700

Data Index: 1326783 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8897. Min Act: -0.1700

Data Index: 2575707 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.8337. Min Act: -0.1700

Data Index: 5083537 (Open Web Text)

Max Activating Token Index: 920

Text #9

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7758. Min Act: -0.1700

Data Index: 450175 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7730. Min Act: -0.1700

Data Index: 3818992 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7598. Min Act: -0.1700

Data Index: 4658380 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7840. Min Act: -0.1700

Data Index: 5886987 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7669. Min Act: -0.1700

Data Index: 2518265 (Open Web Text)

Max Activating Token Index: 737

Text #14

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7313. Min Act: -0.1700

Data Index: 6873737 (Open Web Text)

Max Activating Token Index: 756

Text #15

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7373. Min Act: -0.1700

Data Index: 617386 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7561. Min Act: -0.1700

Data Index: 608191 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7169. Min Act: -0.1700

Data Index: 6508260 (Open Web Text)

Max Activating Token Index: 388

Text #18

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.7124. Min Act: -0.1700

Data Index: 6551646 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 4.0349. Min Range: -4.0349

Max Act: 3.6872. Min Act: -0.1700

Data Index: 2714964 (Open Web Text)

Max Activating Token Index: 449