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

Dataset: Open Web Text

Neuron 1818 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: 3.3636. Min Range: -3.3636

Max Act: 3.3636. Min Act: -0.1700

Data Index: 3685814 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.2688. Min Act: -0.1700

Data Index: 5377265 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.2574. Min Act: -0.1700

Data Index: 7939847 (Open Web Text)

Max Activating Token Index: 588

Text #3

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.2033. Min Act: -0.1700

Data Index: 3477682 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.1975. Min Act: -0.1700

Data Index: 7168494 (Open Web Text)

Max Activating Token Index: 642

Text #5

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.2342. Min Act: -0.1700

Data Index: 3374818 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.1707. Min Act: -0.1700

Data Index: 8505033 (Open Web Text)

Max Activating Token Index: 70

Text #7

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.2052. Min Act: -0.1700

Data Index: 5666736 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.1045. Min Act: -0.1700

Data Index: 2706317 (Open Web Text)

Max Activating Token Index: 64

Text #9

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0744. Min Act: -0.1700

Data Index: 7106048 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.1066. Min Act: -0.1700

Data Index: 3979336 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0919. Min Act: -0.1700

Data Index: 3435458 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0973. Min Act: -0.1700

Data Index: 4575987 (Open Web Text)

Max Activating Token Index: 759

Text #13

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0589. Min Act: -0.1700

Data Index: 240022 (Open Web Text)

Max Activating Token Index: 557

Text #14

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.1142. Min Act: -0.1700

Data Index: 7667127 (Open Web Text)

Max Activating Token Index: 317

Text #15

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0309. Min Act: -0.1700

Data Index: 4907900 (Open Web Text)

Max Activating Token Index: 729

Text #16

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0467. Min Act: -0.1700

Data Index: 4472015 (Open Web Text)

Max Activating Token Index: 680

Text #17

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0338. Min Act: -0.1700

Data Index: 1706176 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0485. Min Act: -0.1700

Data Index: 55444 (Open Web Text)

Max Activating Token Index: 159

Text #19

Max Range: 3.3636. Min Range: -3.3636

Max Act: 3.0760. Min Act: -0.1700

Data Index: 2729317 (Open Web Text)

Max Activating Token Index: 884