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

Dataset: Open Web Text

Neuron 1557 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: 3.6296. Min Range: -3.6296

Max Act: 3.6296. Min Act: -0.1700

Data Index: 3997991 (Open Web Text)

Max Activating Token Index: 163

Text #1

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.5519. Min Act: -0.1700

Data Index: 5972900 (Open Web Text)

Max Activating Token Index: 446

Text #2

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.5413. Min Act: -0.1700

Data Index: 3088810 (Open Web Text)

Max Activating Token Index: 780

Text #3

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.4825. Min Act: -0.1700

Data Index: 197932 (Open Web Text)

Max Activating Token Index: 306

Text #4

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.4488. Min Act: -0.1700

Data Index: 6970909 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.4642. Min Act: -0.1700

Data Index: 4072588 (Open Web Text)

Max Activating Token Index: 934

Text #6

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.4430. Min Act: -0.1700

Data Index: 713540 (Open Web Text)

Max Activating Token Index: 365

Text #7

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1456055 (Open Web Text)

Max Activating Token Index: 326

Text #8

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.4185. Min Act: -0.1700

Data Index: 3088808 (Open Web Text)

Max Activating Token Index: 285

Text #9

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.3608. Min Act: -0.1700

Data Index: 7160331 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.3159. Min Act: -0.1700

Data Index: 2221737 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2947. Min Act: -0.1700

Data Index: 7311127 (Open Web Text)

Max Activating Token Index: 852

Text #12

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.3398. Min Act: -0.1700

Data Index: 6943001 (Open Web Text)

Max Activating Token Index: 977

Text #13

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2957. Min Act: -0.1700

Data Index: 1774024 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2589. Min Act: -0.1700

Data Index: 5593057 (Open Web Text)

Max Activating Token Index: 661

Text #15

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2705. Min Act: -0.1700

Data Index: 2225806 (Open Web Text)

Max Activating Token Index: 227

Text #16

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2425. Min Act: -0.1700

Data Index: 3067389 (Open Web Text)

Max Activating Token Index: 486

Text #17

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2853. Min Act: -0.1700

Data Index: 5214900 (Open Web Text)

Max Activating Token Index: 344

Text #18

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2753. Min Act: -0.1700

Data Index: 1020208 (Open Web Text)

Max Activating Token Index: 978

Text #19

Max Range: 3.6296. Min Range: -3.6296

Max Act: 3.2390. Min Act: -0.1700

Data Index: 4398416 (Open Web Text)

Max Activating Token Index: 260