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

Dataset: Open Web Text

Neuron 278 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: 3.1758. Min Range: -3.1758

Max Act: 3.1758. Min Act: -0.1700

Data Index: 1929022 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0983. Min Act: -0.1700

Data Index: 7322007 (Open Web Text)

Max Activating Token Index: 576

Text #2

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.1184. Min Act: -0.1700

Data Index: 5441762 (Open Web Text)

Max Activating Token Index: 333

Text #3

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.1070. Min Act: -0.1700

Data Index: 6567937 (Open Web Text)

Max Activating Token Index: 402

Text #4

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0685. Min Act: -0.1700

Data Index: 6325460 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0689. Min Act: -0.1700

Data Index: 1159662 (Open Web Text)

Max Activating Token Index: 321

Text #6

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0307. Min Act: -0.1700

Data Index: 6913766 (Open Web Text)

Max Activating Token Index: 70

Text #7

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0270. Min Act: -0.1700

Data Index: 4021207 (Open Web Text)

Max Activating Token Index: 686

Text #8

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9964. Min Act: -0.1700

Data Index: 6305662 (Open Web Text)

Max Activating Token Index: 180

Text #9

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0022. Min Act: -0.1700

Data Index: 4124864 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9974. Min Act: -0.1700

Data Index: 1559612 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9811. Min Act: -0.1700

Data Index: 6776767 (Open Web Text)

Max Activating Token Index: 117

Text #12

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9668. Min Act: -0.1700

Data Index: 2592633 (Open Web Text)

Max Activating Token Index: 288

Text #13

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9800. Min Act: -0.1700

Data Index: 2837015 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9575. Min Act: -0.1700

Data Index: 8626880 (Open Web Text)

Max Activating Token Index: 770

Text #15

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9501. Min Act: -0.1700

Data Index: 342784 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9361. Min Act: -0.1700

Data Index: 4463797 (Open Web Text)

Max Activating Token Index: 149

Text #17

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9279. Min Act: -0.1700

Data Index: 2755060 (Open Web Text)

Max Activating Token Index: 687

Text #18

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9432. Min Act: -0.1700

Data Index: 1457036 (Open Web Text)

Max Activating Token Index: 877

Text #19

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9336. Min Act: -0.1700

Data Index: 1933183 (Open Web Text)

Max Activating Token Index: 794