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

Dataset: Open Web Text

Neuron 1691 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: 4.3687. Min Range: -4.3687

Max Act: 4.3687. Min Act: -0.1700

Data Index: 3132920 (Open Web Text)

Max Activating Token Index: 333

Text #1

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.3348. Min Act: -0.1700

Data Index: 8341138 (Open Web Text)

Max Activating Token Index: 614

Text #2

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.3450. Min Act: -0.1700

Data Index: 6141257 (Open Web Text)

Max Activating Token Index: 952

Text #3

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.1751. Min Act: -0.1700

Data Index: 4874816 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2200. Min Act: -0.1700

Data Index: 1824976 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2078. Min Act: -0.1700

Data Index: 1083506 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.1629. Min Act: -0.1700

Data Index: 7602531 (Open Web Text)

Max Activating Token Index: 149

Text #7

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.1268. Min Act: -0.1700

Data Index: 6616144 (Open Web Text)

Max Activating Token Index: 810

Text #8

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0794. Min Act: -0.1700

Data Index: 6896634 (Open Web Text)

Max Activating Token Index: 187

Text #9

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.1639. Min Act: -0.1700

Data Index: 2245895 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0867. Min Act: -0.1700

Data Index: 6280360 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0944. Min Act: -0.1700

Data Index: 5569812 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0814. Min Act: -0.1700

Data Index: 4355248 (Open Web Text)

Max Activating Token Index: 105

Text #13

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0390. Min Act: -0.1700

Data Index: 5009658 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0880. Min Act: -0.1700

Data Index: 5694365 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0020. Min Act: -0.1700

Data Index: 5345384 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0240. Min Act: -0.1700

Data Index: 8791259 (Open Web Text)

Max Activating Token Index: 486

Text #17

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0488. Min Act: -0.1700

Data Index: 8542023 (Open Web Text)

Max Activating Token Index: 345

Text #18

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0110. Min Act: -0.1700

Data Index: 2473695 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0173. Min Act: -0.1700

Data Index: 2500799 (Open Web Text)

Max Activating Token Index: 341