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

Dataset: Open Web Text

Neuron 1990 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: 4.9249. Min Range: -4.9249

Max Act: 4.9249. Min Act: -0.1700

Data Index: 5276075 (Open Web Text)

Max Activating Token Index: 334

Text #1

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.9146. Min Act: -0.1700

Data Index: 8409846 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.8955. Min Act: -0.1700

Data Index: 7342826 (Open Web Text)

Max Activating Token Index: 296

Text #3

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.8667. Min Act: -0.1700

Data Index: 5477063 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.8435. Min Act: -0.1700

Data Index: 1526584 (Open Web Text)

Max Activating Token Index: 768

Text #5

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.8283. Min Act: -0.1700

Data Index: 3198108 (Open Web Text)

Max Activating Token Index: 250

Text #6

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.8107. Min Act: -0.1700

Data Index: 4637037 (Open Web Text)

Max Activating Token Index: 312

Text #7

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.8449. Min Act: -0.1700

Data Index: 3663001 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.8210. Min Act: -0.1700

Data Index: 4795621 (Open Web Text)

Max Activating Token Index: 953

Text #9

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7826. Min Act: -0.1700

Data Index: 949123 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7727. Min Act: -0.1700

Data Index: 8565091 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7514. Min Act: -0.1700

Data Index: 5444153 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7217. Min Act: -0.1700

Data Index: 4119651 (Open Web Text)

Max Activating Token Index: 176

Text #13

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7572. Min Act: -0.1700

Data Index: 3299529 (Open Web Text)

Max Activating Token Index: 551

Text #14

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7659. Min Act: -0.1700

Data Index: 3176277 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7663. Min Act: -0.1700

Data Index: 1321584 (Open Web Text)

Max Activating Token Index: 911

Text #16

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7437. Min Act: -0.1700

Data Index: 3996259 (Open Web Text)

Max Activating Token Index: 32

Text #17

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7239. Min Act: -0.1700

Data Index: 4203490 (Open Web Text)

Max Activating Token Index: 959

Text #18

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7198. Min Act: -0.1700

Data Index: 644443 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 4.9249. Min Range: -4.9249

Max Act: 4.7290. Min Act: -0.1700

Data Index: 5279138 (Open Web Text)

Max Activating Token Index: 352