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

Dataset: Open Web Text

Neuron 253 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: 1.3177. Min Range: -1.3177

Max Act: 1.3177. Min Act: -0.1700

Data Index: 3976993 (Open Web Text)

Max Activating Token Index: 496

Text #1

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.3010. Min Act: -0.1700

Data Index: 3976990 (Open Web Text)

Max Activating Token Index: 499

Text #2

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.3016. Min Act: -0.1700

Data Index: 3976981 (Open Web Text)

Max Activating Token Index: 494

Text #3

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2820. Min Act: -0.1700

Data Index: 3977001 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2822. Min Act: -0.1700

Data Index: 3976989 (Open Web Text)

Max Activating Token Index: 500

Text #5

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2850. Min Act: -0.1700

Data Index: 3976983 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2883. Min Act: -0.1700

Data Index: 3976979 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2773. Min Act: -0.1700

Data Index: 3976978 (Open Web Text)

Max Activating Token Index: 497

Text #8

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2819. Min Act: -0.1700

Data Index: 3976988 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2929. Min Act: -0.1700

Data Index: 3976997 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2752. Min Act: -0.1700

Data Index: 3976984 (Open Web Text)

Max Activating Token Index: 505

Text #11

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2805. Min Act: -0.1700

Data Index: 3976987 (Open Web Text)

Max Activating Token Index: 502

Text #12

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2887. Min Act: -0.1700

Data Index: 3976974 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2829. Min Act: -0.1700

Data Index: 3976994 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2912. Min Act: -0.1700

Data Index: 3976995 (Open Web Text)

Max Activating Token Index: 494

Text #15

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2838. Min Act: -0.1700

Data Index: 3976975 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2951. Min Act: -0.1700

Data Index: 3976976 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2655. Min Act: -0.1700

Data Index: 3976977 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2604. Min Act: -0.1700

Data Index: 3976985 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 1.3177. Min Range: -1.3177

Max Act: 1.2686. Min Act: -0.1700

Data Index: 446491 (Open Web Text)

Max Activating Token Index: 500