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

Dataset: Open Web Text

Neuron 2173 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: 5.4692. Min Range: -5.4692

Max Act: 5.4692. Min Act: -0.1700

Data Index: 2312705 (Open Web Text)

Max Activating Token Index: 103

Text #1

Max Range: 5.4692. Min Range: -5.4692

Max Act: 5.0579. Min Act: -0.1700

Data Index: 2580577 (Open Web Text)

Max Activating Token Index: 708

Text #2

Max Range: 5.4692. Min Range: -5.4692

Max Act: 5.0051. Min Act: -0.1700

Data Index: 8245606 (Open Web Text)

Max Activating Token Index: 967

Text #3

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9977. Min Act: -0.1700

Data Index: 6689302 (Open Web Text)

Max Activating Token Index: 523

Text #4

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9787. Min Act: -0.1700

Data Index: 2956697 (Open Web Text)

Max Activating Token Index: 880

Text #5

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9311. Min Act: -0.1700

Data Index: 6028663 (Open Web Text)

Max Activating Token Index: 652

Text #6

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9602. Min Act: -0.1700

Data Index: 7080999 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9660. Min Act: -0.1700

Data Index: 7110926 (Open Web Text)

Max Activating Token Index: 642

Text #8

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9050. Min Act: -0.1700

Data Index: 6251795 (Open Web Text)

Max Activating Token Index: 157

Text #9

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9314. Min Act: -0.1700

Data Index: 138654 (Open Web Text)

Max Activating Token Index: 307

Text #10

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8639. Min Act: -0.1700

Data Index: 2955606 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.9410. Min Act: -0.1700

Data Index: 3676045 (Open Web Text)

Max Activating Token Index: 236

Text #12

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8928. Min Act: -0.1700

Data Index: 1962508 (Open Web Text)

Max Activating Token Index: 114

Text #13

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8710. Min Act: -0.1700

Data Index: 7787443 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8796. Min Act: -0.1700

Data Index: 3842391 (Open Web Text)

Max Activating Token Index: 410

Text #15

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8531. Min Act: -0.1700

Data Index: 5577753 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8034. Min Act: -0.1700

Data Index: 3247985 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8469. Min Act: -0.1700

Data Index: 2664667 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8505. Min Act: -0.1700

Data Index: 3931831 (Open Web Text)

Max Activating Token Index: 135

Text #19

Max Range: 5.4692. Min Range: -5.4692

Max Act: 4.8926. Min Act: -0.1700

Data Index: 1494664 (Open Web Text)

Max Activating Token Index: 707