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

Dataset: Open Web Text

Neuron 2879 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: 3.5430. Min Range: -3.5430

Max Act: 3.5430. Min Act: -0.1700

Data Index: 4171162 (Open Web Text)

Max Activating Token Index: 182

Text #1

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.4856. Min Act: -0.1700

Data Index: 6505886 (Open Web Text)

Max Activating Token Index: 680

Text #2

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.4524. Min Act: -0.1700

Data Index: 5849800 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.4422. Min Act: -0.1700

Data Index: 7815943 (Open Web Text)

Max Activating Token Index: 820

Text #4

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.4325. Min Act: -0.1700

Data Index: 4220771 (Open Web Text)

Max Activating Token Index: 643

Text #5

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.4340. Min Act: -0.1700

Data Index: 6604503 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3886. Min Act: -0.1700

Data Index: 3860022 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.4035. Min Act: -0.1700

Data Index: 2792042 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3979. Min Act: -0.1700

Data Index: 4120524 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1037617 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3628. Min Act: -0.1700

Data Index: 5731134 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3728. Min Act: -0.1700

Data Index: 3681039 (Open Web Text)

Max Activating Token Index: 700

Text #12

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3484. Min Act: -0.1700

Data Index: 5686665 (Open Web Text)

Max Activating Token Index: 71

Text #13

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3239. Min Act: -0.1700

Data Index: 1984179 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3269. Min Act: -0.1700

Data Index: 4573648 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3431. Min Act: -0.1700

Data Index: 1421960 (Open Web Text)

Max Activating Token Index: 77

Text #16

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3387. Min Act: -0.1700

Data Index: 5127512 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3240. Min Act: -0.1700

Data Index: 8203380 (Open Web Text)

Max Activating Token Index: 947

Text #18

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3099. Min Act: -0.1700

Data Index: 19198 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.3108. Min Act: -0.1700

Data Index: 5287460 (Open Web Text)

Max Activating Token Index: 433