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

Dataset: Open Web Text

Neuron 2803 in Layer 2

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: 4.8700. Min Range: -4.8700

Max Act: 4.8552. Min Act: -0.1700

Data Index: 6700528 (Open Web Text)

Max Activating Token Index: 329

Text #1

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.8700. Min Act: -0.1700

Data Index: 841699 (Open Web Text)

Max Activating Token Index: 658

Text #2

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.8349. Min Act: -0.1700

Data Index: 7785892 (Open Web Text)

Max Activating Token Index: 164

Text #3

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.8390. Min Act: -0.1700

Data Index: 8796787 (Open Web Text)

Max Activating Token Index: 769

Text #4

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.8344. Min Act: -0.1700

Data Index: 841698 (Open Web Text)

Max Activating Token Index: 745

Text #5

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.8198. Min Act: -0.1700

Data Index: 5310500 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.8242. Min Act: -0.1700

Data Index: 6264573 (Open Web Text)

Max Activating Token Index: 864

Text #7

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7723. Min Act: -0.1700

Data Index: 5329338 (Open Web Text)

Max Activating Token Index: 144

Text #8

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7669. Min Act: -0.1700

Data Index: 1007216 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7683. Min Act: -0.1700

Data Index: 7493550 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7677. Min Act: -0.1700

Data Index: 907917 (Open Web Text)

Max Activating Token Index: 387

Text #11

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7854. Min Act: -0.1700

Data Index: 6185757 (Open Web Text)

Max Activating Token Index: 245

Text #12

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7322. Min Act: -0.1700

Data Index: 3530651 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7527. Min Act: -0.1700

Data Index: 6494551 (Open Web Text)

Max Activating Token Index: 381

Text #14

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7638. Min Act: -0.1700

Data Index: 8812181 (Open Web Text)

Max Activating Token Index: 533

Text #15

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7366. Min Act: -0.1700

Data Index: 2072210 (Open Web Text)

Max Activating Token Index: 240

Text #16

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7319. Min Act: -0.1700

Data Index: 8676254 (Open Web Text)

Max Activating Token Index: 553

Text #17

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7121. Min Act: -0.1700

Data Index: 2195126 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7166. Min Act: -0.1700

Data Index: 3045838 (Open Web Text)

Max Activating Token Index: 432

Text #19

Max Range: 4.8700. Min Range: -4.8700

Max Act: 4.7324. Min Act: -0.1700

Data Index: 1541442 (Open Web Text)

Max Activating Token Index: 415