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

Dataset: Open Web Text

Neuron 112 in Layer 0

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: 3.7333. Min Range: -3.7333

Max Act: 3.7333. Min Act: -0.1700

Data Index: 1243759 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.7189. Min Act: -0.1700

Data Index: 2508879 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.6547. Min Act: -0.1700

Data Index: 3417579 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.6601. Min Act: -0.1700

Data Index: 4446249 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.6524. Min Act: -0.1700

Data Index: 8371255 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.6742. Min Act: -0.1700

Data Index: 6112524 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.6115. Min Act: -0.1700

Data Index: 268263 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.6358. Min Act: -0.1700

Data Index: 184348 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5884. Min Act: -0.1700

Data Index: 3452114 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.6051. Min Act: -0.1700

Data Index: 7645154 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5665. Min Act: -0.1700

Data Index: 5019275 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5665. Min Act: -0.1700

Data Index: 1991502 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5665. Min Act: -0.1700

Data Index: 5561473 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5665. Min Act: -0.1700

Data Index: 2436476 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5483. Min Act: -0.1700

Data Index: 2642045 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5764. Min Act: -0.1700

Data Index: 3211234 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5683. Min Act: -0.1700

Data Index: 3218022 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5572. Min Act: -0.1700

Data Index: 916153 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5647. Min Act: -0.1700

Data Index: 6549211 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.7333. Min Range: -3.7333

Max Act: 3.5665. Min Act: -0.1700

Data Index: 39844 (Open Web Text)

Max Activating Token Index: 2