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

Dataset: Open Web Text

Neuron 898 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: 3.0717. Min Range: -3.0717

Max Act: 3.0717. Min Act: -0.1700

Data Index: 152090 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.0717. Min Range: -3.0717

Max Act: 3.0286. Min Act: -0.1700

Data Index: 1879514 (Open Web Text)

Max Activating Token Index: 767

Text #2

Max Range: 3.0717. Min Range: -3.0717

Max Act: 3.0001. Min Act: -0.1700

Data Index: 1304109 (Open Web Text)

Max Activating Token Index: 759

Text #3

Max Range: 3.0717. Min Range: -3.0717

Max Act: 3.0057. Min Act: -0.1700

Data Index: 5969645 (Open Web Text)

Max Activating Token Index: 817

Text #4

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9848. Min Act: -0.1700

Data Index: 8782742 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9760. Min Act: -0.1700

Data Index: 8641259 (Open Web Text)

Max Activating Token Index: 578

Text #6

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9291. Min Act: -0.1700

Data Index: 3407515 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9562. Min Act: -0.1700

Data Index: 456944 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9319. Min Act: -0.1700

Data Index: 849154 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9582. Min Act: -0.1700

Data Index: 618216 (Open Web Text)

Max Activating Token Index: 813

Text #10

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9498. Min Act: -0.1700

Data Index: 3702786 (Open Web Text)

Max Activating Token Index: 85

Text #11

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9153. Min Act: -0.1700

Data Index: 7498478 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9129. Min Act: -0.1700

Data Index: 4184885 (Open Web Text)

Max Activating Token Index: 927

Text #13

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8636. Min Act: -0.1700

Data Index: 8054436 (Open Web Text)

Max Activating Token Index: 802

Text #14

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8683. Min Act: -0.1700

Data Index: 702486 (Open Web Text)

Max Activating Token Index: 262

Text #15

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8682. Min Act: -0.1700

Data Index: 1967386 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9006. Min Act: -0.1700

Data Index: 7570209 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8676. Min Act: -0.1700

Data Index: 8422735 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8287. Min Act: -0.1700

Data Index: 8228873 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8526. Min Act: -0.1700

Data Index: 8193130 (Open Web Text)

Max Activating Token Index: 124