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

Dataset: Open Web Text

Neuron 503 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: 3.5074. Min Range: -3.5074

Max Act: 3.5074. Min Act: -0.1700

Data Index: 2622871 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.4934. Min Act: -0.1700

Data Index: 2424394 (Open Web Text)

Max Activating Token Index: 176

Text #2

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.4007. Min Act: -0.1700

Data Index: 2520035 (Open Web Text)

Max Activating Token Index: 738

Text #3

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.4293. Min Act: -0.1700

Data Index: 760147 (Open Web Text)

Max Activating Token Index: 321

Text #4

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.4261. Min Act: -0.1700

Data Index: 1353826 (Open Web Text)

Max Activating Token Index: 918

Text #5

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3909. Min Act: -0.1700

Data Index: 1662751 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3955. Min Act: -0.1700

Data Index: 7202811 (Open Web Text)

Max Activating Token Index: 493

Text #7

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3694. Min Act: -0.1700

Data Index: 4090705 (Open Web Text)

Max Activating Token Index: 943

Text #8

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3785. Min Act: -0.1700

Data Index: 3929490 (Open Web Text)

Max Activating Token Index: 258

Text #9

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3721. Min Act: -0.1700

Data Index: 3660474 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3783. Min Act: -0.1700

Data Index: 4995819 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3437. Min Act: -0.1700

Data Index: 5486320 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3409. Min Act: -0.1700

Data Index: 2682038 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3515. Min Act: -0.1700

Data Index: 8305241 (Open Web Text)

Max Activating Token Index: 570

Text #14

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3662. Min Act: -0.1700

Data Index: 1506802 (Open Web Text)

Max Activating Token Index: 338

Text #15

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3487. Min Act: -0.1700

Data Index: 6168730 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3949. Min Act: -0.1700

Data Index: 5848715 (Open Web Text)

Max Activating Token Index: 624

Text #17

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3268. Min Act: -0.1700

Data Index: 7342814 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3474. Min Act: -0.1700

Data Index: 6462112 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3150. Min Act: -0.1700

Data Index: 28640 (Open Web Text)

Max Activating Token Index: 1022