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

Dataset: Open Web Text

Neuron 2786 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: 3.6223. Min Range: -3.6223

Max Act: 3.6223. Min Act: -0.1700

Data Index: 1115990 (Open Web Text)

Max Activating Token Index: 298

Text #1

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.6170. Min Act: -0.1700

Data Index: 3831675 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.6050. Min Act: -0.1700

Data Index: 3533454 (Open Web Text)

Max Activating Token Index: 1000

Text #3

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5721. Min Act: -0.1700

Data Index: 1755742 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5604. Min Act: -0.1700

Data Index: 5291722 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5559. Min Act: -0.1700

Data Index: 7030244 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5259. Min Act: -0.1700

Data Index: 5936740 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5042. Min Act: -0.1700

Data Index: 1147283 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5291. Min Act: -0.1700

Data Index: 544620 (Open Web Text)

Max Activating Token Index: 870

Text #9

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5205. Min Act: -0.1700

Data Index: 6354852 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5049. Min Act: -0.1700

Data Index: 5279804 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.5276. Min Act: -0.1700

Data Index: 3534094 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4897. Min Act: -0.1700

Data Index: 4984767 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4853. Min Act: -0.1700

Data Index: 7692425 (Open Web Text)

Max Activating Token Index: 188

Text #14

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4735. Min Act: -0.1700

Data Index: 6591823 (Open Web Text)

Max Activating Token Index: 286

Text #15

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4749. Min Act: -0.1700

Data Index: 2750071 (Open Web Text)

Max Activating Token Index: 727

Text #16

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4623. Min Act: -0.1700

Data Index: 2106966 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4681. Min Act: -0.1700

Data Index: 5024537 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4412. Min Act: -0.1700

Data Index: 2617563 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.4198. Min Act: -0.1700

Data Index: 3488088 (Open Web Text)

Max Activating Token Index: 364