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

Dataset: Open Web Text

Neuron 678 in Layer 1

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: 1.9191. Min Range: -1.9191

Max Act: 1.9191. Min Act: -0.1700

Data Index: 1092534 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.9010. Min Act: -0.1700

Data Index: 3536927 (Open Web Text)

Max Activating Token Index: 242

Text #2

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8876. Min Act: -0.1700

Data Index: 3375047 (Open Web Text)

Max Activating Token Index: 90

Text #3

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8629. Min Act: -0.1700

Data Index: 7033753 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8585. Min Act: -0.1700

Data Index: 7021624 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8376. Min Act: -0.1700

Data Index: 640873 (Open Web Text)

Max Activating Token Index: 985

Text #6

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8463. Min Act: -0.1700

Data Index: 8495375 (Open Web Text)

Max Activating Token Index: 96

Text #7

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8323. Min Act: -0.1700

Data Index: 5423343 (Open Web Text)

Max Activating Token Index: 484

Text #8

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8279. Min Act: -0.1700

Data Index: 5684712 (Open Web Text)

Max Activating Token Index: 227

Text #9

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8434. Min Act: -0.1700

Data Index: 5055763 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8291. Min Act: -0.1700

Data Index: 2681988 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8438. Min Act: -0.1700

Data Index: 3321790 (Open Web Text)

Max Activating Token Index: 509

Text #12

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8037. Min Act: -0.1700

Data Index: 535243 (Open Web Text)

Max Activating Token Index: 855

Text #13

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8019. Min Act: -0.1700

Data Index: 6218100 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.8126. Min Act: -0.1700

Data Index: 3606470 (Open Web Text)

Max Activating Token Index: 287

Text #15

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.7944. Min Act: -0.1700

Data Index: 1045244 (Open Web Text)

Max Activating Token Index: 56

Text #16

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.7766. Min Act: -0.1700

Data Index: 6148242 (Open Web Text)

Max Activating Token Index: 773

Text #17

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.7944. Min Act: -0.1700

Data Index: 434509 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.7806. Min Act: -0.1700

Data Index: 3675290 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 1.9191. Min Range: -1.9191

Max Act: 1.7871. Min Act: -0.1700

Data Index: 4199351 (Open Web Text)

Max Activating Token Index: 431