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

Dataset: Open Web Text

Neuron 827 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: 5.4394. Min Range: -5.4394

Max Act: 5.4394. Min Act: -0.1700

Data Index: 6039396 (Open Web Text)

Max Activating Token Index: 984

Text #1

Max Range: 5.4394. Min Range: -5.4394

Max Act: 5.3252. Min Act: -0.1700

Data Index: 7999632 (Open Web Text)

Max Activating Token Index: 931

Text #2

Max Range: 5.4394. Min Range: -5.4394

Max Act: 5.1274. Min Act: -0.1700

Data Index: 7872556 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 5.4394. Min Range: -5.4394

Max Act: 5.0830. Min Act: -0.1700

Data Index: 1402157 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.9717. Min Act: -0.1700

Data Index: 4755392 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.9033. Min Act: -0.1700

Data Index: 6822791 (Open Web Text)

Max Activating Token Index: 281

Text #6

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.8466. Min Act: -0.1700

Data Index: 4870396 (Open Web Text)

Max Activating Token Index: 290

Text #7

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.7836. Min Act: -0.1700

Data Index: 5258004 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.7851. Min Act: -0.1700

Data Index: 4533936 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.7743. Min Act: -0.1700

Data Index: 1144127 (Open Web Text)

Max Activating Token Index: 700

Text #10

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6541. Min Act: -0.1700

Data Index: 6169431 (Open Web Text)

Max Activating Token Index: 725

Text #11

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6602. Min Act: -0.1700

Data Index: 5916888 (Open Web Text)

Max Activating Token Index: 789

Text #12

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6816. Min Act: -0.1700

Data Index: 7801131 (Open Web Text)

Max Activating Token Index: 88

Text #13

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6895. Min Act: -0.1700

Data Index: 8121591 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6523. Min Act: -0.1700

Data Index: 1223936 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.5682. Min Act: -0.1700

Data Index: 8254917 (Open Web Text)

Max Activating Token Index: 352

Text #16

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6590. Min Act: -0.1700

Data Index: 5401533 (Open Web Text)

Max Activating Token Index: 259

Text #17

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6369. Min Act: -0.1700

Data Index: 4448768 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6019. Min Act: -0.1700

Data Index: 6282950 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 5.4394. Min Range: -5.4394

Max Act: 4.6848. Min Act: -0.1700

Data Index: 7985435 (Open Web Text)

Max Activating Token Index: 221