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

Dataset: Open Web Text

Neuron 999 in Layer 5

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: 4.4460. Min Range: -4.4460

Max Act: 4.4261. Min Act: -0.1700

Data Index: 7813546 (Open Web Text)

Max Activating Token Index: 791

Text #1

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.4460. Min Act: -0.1700

Data Index: 6665829 (Open Web Text)

Max Activating Token Index: 706

Text #2

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.4040. Min Act: -0.1700

Data Index: 7554511 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.3657. Min Act: -0.1700

Data Index: 4906489 (Open Web Text)

Max Activating Token Index: 110

Text #4

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.3743. Min Act: -0.1700

Data Index: 5715108 (Open Web Text)

Max Activating Token Index: 135

Text #5

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.3261. Min Act: -0.1700

Data Index: 1769465 (Open Web Text)

Max Activating Token Index: 565

Text #6

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.3087. Min Act: -0.1700

Data Index: 756681 (Open Web Text)

Max Activating Token Index: 796

Text #7

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.3102. Min Act: -0.1700

Data Index: 3920819 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2738. Min Act: -0.1700

Data Index: 4212263 (Open Web Text)

Max Activating Token Index: 488

Text #9

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2803. Min Act: -0.1700

Data Index: 6155599 (Open Web Text)

Max Activating Token Index: 561

Text #10

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2668. Min Act: -0.1700

Data Index: 2805257 (Open Web Text)

Max Activating Token Index: 956

Text #11

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2729. Min Act: -0.1700

Data Index: 1241823 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2817. Min Act: -0.1700

Data Index: 5504838 (Open Web Text)

Max Activating Token Index: 565

Text #13

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2520. Min Act: -0.1700

Data Index: 8291694 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2459. Min Act: -0.1700

Data Index: 6228998 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.1794. Min Act: -0.1700

Data Index: 4597761 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.1993. Min Act: -0.1700

Data Index: 4696272 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2079. Min Act: -0.1700

Data Index: 630616 (Open Web Text)

Max Activating Token Index: 710

Text #18

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2079. Min Act: -0.1700

Data Index: 570979 (Open Web Text)

Max Activating Token Index: 56

Text #19

Max Range: 4.4460. Min Range: -4.4460

Max Act: 4.2254. Min Act: -0.1700

Data Index: 4769897 (Open Web Text)

Max Activating Token Index: 999