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

Dataset: Open Web Text

Neuron 464 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: 3.6145. Min Range: -3.6145

Max Act: 3.6145. Min Act: -0.1700

Data Index: 7218445 (Open Web Text)

Max Activating Token Index: 969

Text #1

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5773. Min Act: -0.1700

Data Index: 2743659 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5659. Min Act: -0.1700

Data Index: 8235531 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5231. Min Act: -0.1700

Data Index: 5347815 (Open Web Text)

Max Activating Token Index: 364

Text #4

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5193. Min Act: -0.1700

Data Index: 2937389 (Open Web Text)

Max Activating Token Index: 775

Text #5

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.5203. Min Act: -0.1700

Data Index: 7183860 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4579. Min Act: -0.1700

Data Index: 5111046 (Open Web Text)

Max Activating Token Index: 937

Text #7

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4490. Min Act: -0.1700

Data Index: 8095508 (Open Web Text)

Max Activating Token Index: 935

Text #8

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4332. Min Act: -0.1700

Data Index: 4588995 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4387. Min Act: -0.1700

Data Index: 7234704 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4367. Min Act: -0.1700

Data Index: 2569959 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4129. Min Act: -0.1700

Data Index: 8382448 (Open Web Text)

Max Activating Token Index: 322

Text #12

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4343. Min Act: -0.1700

Data Index: 1079223 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4076. Min Act: -0.1700

Data Index: 2503592 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4131. Min Act: -0.1700

Data Index: 1987131 (Open Web Text)

Max Activating Token Index: 195

Text #15

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.3992. Min Act: -0.1700

Data Index: 4625709 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4092. Min Act: -0.1700

Data Index: 3993327 (Open Web Text)

Max Activating Token Index: 750

Text #17

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4122. Min Act: -0.1700

Data Index: 7206049 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.3991. Min Act: -0.1700

Data Index: 6278064 (Open Web Text)

Max Activating Token Index: 309

Text #19

Max Range: 3.6145. Min Range: -3.6145

Max Act: 3.4349. Min Act: -0.1700

Data Index: 1551709 (Open Web Text)

Max Activating Token Index: 374