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

Dataset: Open Web Text

Neuron 2186 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: 3.5704. Min Range: -3.5704

Max Act: 3.5704. Min Act: -0.1700

Data Index: 7314134 (Open Web Text)

Max Activating Token Index: 612

Text #1

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5586. Min Act: -0.1700

Data Index: 6340554 (Open Web Text)

Max Activating Token Index: 705

Text #2

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5549. Min Act: -0.1700

Data Index: 1525715 (Open Web Text)

Max Activating Token Index: 1018

Text #3

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5520. Min Act: -0.1700

Data Index: 8214578 (Open Web Text)

Max Activating Token Index: 227

Text #4

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5565. Min Act: -0.1700

Data Index: 3465005 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5325. Min Act: -0.1700

Data Index: 1237146 (Open Web Text)

Max Activating Token Index: 299

Text #6

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5332. Min Act: -0.1700

Data Index: 6221355 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5039. Min Act: -0.1700

Data Index: 5901316 (Open Web Text)

Max Activating Token Index: 895

Text #8

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5273. Min Act: -0.1700

Data Index: 3385011 (Open Web Text)

Max Activating Token Index: 748

Text #9

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4957. Min Act: -0.1700

Data Index: 7739922 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4752. Min Act: -0.1700

Data Index: 7646233 (Open Web Text)

Max Activating Token Index: 1018

Text #11

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4979. Min Act: -0.1700

Data Index: 365856 (Open Web Text)

Max Activating Token Index: 1020

Text #12

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4849. Min Act: -0.1700

Data Index: 6197586 (Open Web Text)

Max Activating Token Index: 867

Text #13

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.5060. Min Act: -0.1700

Data Index: 3805244 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4823. Min Act: -0.1700

Data Index: 5558485 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4940. Min Act: -0.1700

Data Index: 1839622 (Open Web Text)

Max Activating Token Index: 948

Text #16

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4590. Min Act: -0.1700

Data Index: 862265 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4715. Min Act: -0.1700

Data Index: 372762 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4776. Min Act: -0.1700

Data Index: 2492139 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4748. Min Act: -0.1700

Data Index: 5934096 (Open Web Text)

Max Activating Token Index: 621