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

Dataset: Open Web Text

Neuron 2491 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: 1.4935. Min Range: -1.4935

Max Act: 1.4935. Min Act: -0.1700

Data Index: 3453020 (Open Web Text)

Max Activating Token Index: 845

Text #1

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4827. Min Act: -0.1700

Data Index: 2299186 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4677. Min Act: -0.1700

Data Index: 5572339 (Open Web Text)

Max Activating Token Index: 791

Text #3

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4663. Min Act: -0.1700

Data Index: 4496074 (Open Web Text)

Max Activating Token Index: 631

Text #4

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4632. Min Act: -0.1700

Data Index: 3880780 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4608. Min Act: -0.1700

Data Index: 3199891 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4596. Min Act: -0.1700

Data Index: 1174957 (Open Web Text)

Max Activating Token Index: 863

Text #7

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4562. Min Act: -0.1700

Data Index: 4699 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4414. Min Act: -0.1700

Data Index: 2891021 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4451. Min Act: -0.1700

Data Index: 889211 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4448. Min Act: -0.1700

Data Index: 1589036 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4340. Min Act: -0.1700

Data Index: 2376073 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4420. Min Act: -0.1700

Data Index: 28833 (Open Web Text)

Max Activating Token Index: 643

Text #13

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4229. Min Act: -0.1700

Data Index: 5440912 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4284. Min Act: -0.1700

Data Index: 578992 (Open Web Text)

Max Activating Token Index: 592

Text #15

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4134. Min Act: -0.1700

Data Index: 4131065 (Open Web Text)

Max Activating Token Index: 421

Text #16

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4150. Min Act: -0.1700

Data Index: 4159128 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4210. Min Act: -0.1700

Data Index: 3394342 (Open Web Text)

Max Activating Token Index: 157

Text #18

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4203. Min Act: -0.1700

Data Index: 5116001 (Open Web Text)

Max Activating Token Index: 420

Text #19

Max Range: 1.4935. Min Range: -1.4935

Max Act: 1.4196. Min Act: -0.1700

Data Index: 3543295 (Open Web Text)

Max Activating Token Index: 15