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

Dataset: Open Web Text

Neuron 1184 in Layer 6

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: 5.0857. Min Range: -5.0857

Max Act: 5.0857. Min Act: -0.1700

Data Index: 3645411 (Open Web Text)

Max Activating Token Index: 841

Text #1

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.8682. Min Act: -0.1700

Data Index: 2460993 (Open Web Text)

Max Activating Token Index: 59

Text #2

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.7297. Min Act: -0.1700

Data Index: 4163528 (Open Web Text)

Max Activating Token Index: 605

Text #3

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.7054. Min Act: -0.1700

Data Index: 1561143 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6776. Min Act: -0.1700

Data Index: 5353793 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6418. Min Act: -0.1700

Data Index: 8166460 (Open Web Text)

Max Activating Token Index: 1011

Text #6

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6739. Min Act: -0.1700

Data Index: 5800920 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6599. Min Act: -0.1700

Data Index: 2353337 (Open Web Text)

Max Activating Token Index: 935

Text #8

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6676. Min Act: -0.1700

Data Index: 7114183 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6397. Min Act: -0.1700

Data Index: 4037179 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.5930. Min Act: -0.1700

Data Index: 3429659 (Open Web Text)

Max Activating Token Index: 989

Text #11

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6293. Min Act: -0.1700

Data Index: 2448729 (Open Web Text)

Max Activating Token Index: 852

Text #12

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6447. Min Act: -0.1700

Data Index: 2390244 (Open Web Text)

Max Activating Token Index: 701

Text #13

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.6193. Min Act: -0.1700

Data Index: 5793542 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.5700. Min Act: -0.1700

Data Index: 4772923 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.5581. Min Act: -0.1700

Data Index: 675079 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.5658. Min Act: -0.1700

Data Index: 7437927 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.5479. Min Act: -0.1700

Data Index: 7642406 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.5761. Min Act: -0.1700

Data Index: 3101921 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 5.0857. Min Range: -5.0857

Max Act: 4.5614. Min Act: -0.1700

Data Index: 2210879 (Open Web Text)

Max Activating Token Index: 25