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

Dataset: Open Web Text

Neuron 1856 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: 1.9159. Min Range: -1.9159

Max Act: 1.9159. Min Act: -0.1696

Data Index: 1472560 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8908. Min Act: -0.1700

Data Index: 4162729 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8697. Min Act: -0.1700

Data Index: 657651 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8613. Min Act: -0.1700

Data Index: 1472557 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8553. Min Act: -0.1700

Data Index: 1225607 (Open Web Text)

Max Activating Token Index: 173

Text #5

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8447. Min Act: -0.1700

Data Index: 240280 (Open Web Text)

Max Activating Token Index: 561

Text #6

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8546. Min Act: -0.1700

Data Index: 2751258 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8388. Min Act: -0.1700

Data Index: 8673148 (Open Web Text)

Max Activating Token Index: 469

Text #8

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8254. Min Act: -0.1700

Data Index: 7820767 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8304. Min Act: -0.1700

Data Index: 1465175 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8205. Min Act: -0.1700

Data Index: 3628902 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8207. Min Act: -0.1700

Data Index: 1405119 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8263. Min Act: -0.1700

Data Index: 4478493 (Open Web Text)

Max Activating Token Index: 88

Text #13

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8226. Min Act: -0.1700

Data Index: 6173279 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8144. Min Act: -0.1698

Data Index: 937092 (Open Web Text)

Max Activating Token Index: 804

Text #15

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8134. Min Act: -0.1700

Data Index: 225696 (Open Web Text)

Max Activating Token Index: 165

Text #16

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.7972. Min Act: -0.1700

Data Index: 4478490 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.7982. Min Act: -0.1700

Data Index: 3484391 (Open Web Text)

Max Activating Token Index: 380

Text #18

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8141. Min Act: -0.1700

Data Index: 4995460 (Open Web Text)

Max Activating Token Index: 714

Text #19

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.8058. Min Act: -0.1700

Data Index: 7746788 (Open Web Text)

Max Activating Token Index: 732