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

Dataset: Open Web Text

Neuron 361 in Layer 3

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: 3.6437. Min Range: -3.6437

Max Act: 3.6437. Min Act: -0.1700

Data Index: 7621136 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5947. Min Act: -0.1700

Data Index: 8158621 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5918. Min Act: -0.1700

Data Index: 6986859 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5423. Min Act: -0.1700

Data Index: 6678135 (Open Web Text)

Max Activating Token Index: 345

Text #4

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4799. Min Act: -0.1700

Data Index: 8378574 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4733. Min Act: -0.1700

Data Index: 7963023 (Open Web Text)

Max Activating Token Index: 656

Text #6

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4652. Min Act: -0.1700

Data Index: 264788 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4461. Min Act: -0.1700

Data Index: 7686445 (Open Web Text)

Max Activating Token Index: 936

Text #8

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4456. Min Act: -0.1700

Data Index: 4956324 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4240. Min Act: -0.1700

Data Index: 6337323 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4329. Min Act: -0.1700

Data Index: 5822978 (Open Web Text)

Max Activating Token Index: 139

Text #11

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4460. Min Act: -0.1700

Data Index: 3964438 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4107. Min Act: -0.1700

Data Index: 865671 (Open Web Text)

Max Activating Token Index: 998

Text #13

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4269. Min Act: -0.1700

Data Index: 1319707 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4266. Min Act: -0.1700

Data Index: 2286016 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4225. Min Act: -0.1700

Data Index: 2667898 (Open Web Text)

Max Activating Token Index: 705

Text #16

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.3935. Min Act: -0.1700

Data Index: 5633749 (Open Web Text)

Max Activating Token Index: 938

Text #17

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.3798. Min Act: -0.1700

Data Index: 7269468 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.3752. Min Act: -0.1700

Data Index: 597368 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.3803. Min Act: -0.1700

Data Index: 327170 (Open Web Text)

Max Activating Token Index: 106