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

Dataset: Open Web Text

Neuron 1482 in Layer 3

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: 4.8661. Min Range: -4.8661

Max Act: 4.8661. Min Act: -0.1700

Data Index: 8759555 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.8475. Min Act: -0.1700

Data Index: 2858921 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.8049. Min Act: -0.1700

Data Index: 3770673 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7766. Min Act: -0.1700

Data Index: 856237 (Open Web Text)

Max Activating Token Index: 794

Text #4

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7803. Min Act: -0.1700

Data Index: 4598790 (Open Web Text)

Max Activating Token Index: 902

Text #5

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7966. Min Act: -0.1700

Data Index: 856244 (Open Web Text)

Max Activating Token Index: 432

Text #6

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7698. Min Act: -0.1700

Data Index: 712287 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7605. Min Act: -0.1700

Data Index: 8117357 (Open Web Text)

Max Activating Token Index: 434

Text #8

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7654. Min Act: -0.1700

Data Index: 856243 (Open Web Text)

Max Activating Token Index: 816

Text #9

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7264. Min Act: -0.1700

Data Index: 2708998 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7325. Min Act: -0.1700

Data Index: 1576837 (Open Web Text)

Max Activating Token Index: 57

Text #11

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7321. Min Act: -0.1700

Data Index: 4598789 (Open Web Text)

Max Activating Token Index: 325

Text #12

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7431. Min Act: -0.1700

Data Index: 3163614 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7139. Min Act: -0.1700

Data Index: 1955018 (Open Web Text)

Max Activating Token Index: 219

Text #14

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7115. Min Act: -0.1700

Data Index: 5458930 (Open Web Text)

Max Activating Token Index: 982

Text #15

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7321. Min Act: -0.1700

Data Index: 2858917 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7273. Min Act: -0.1700

Data Index: 8759556 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7501. Min Act: -0.1700

Data Index: 2858919 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.6906. Min Act: -0.1700

Data Index: 3136879 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 4.8661. Min Range: -4.8661

Max Act: 4.7187. Min Act: -0.1700

Data Index: 3105563 (Open Web Text)

Max Activating Token Index: 396