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

Dataset: Open Web Text

Neuron 862 in Layer 1

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: 1.9575. Min Range: -1.9575

Max Act: 1.9575. Min Act: -0.1700

Data Index: 871467 (Open Web Text)

Max Activating Token Index: 155

Text #1

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8946. Min Act: -0.1700

Data Index: 5661494 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8767. Min Act: -0.1700

Data Index: 742972 (Open Web Text)

Max Activating Token Index: 201

Text #3

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8558. Min Act: -0.1700

Data Index: 5934605 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8450. Min Act: -0.1700

Data Index: 344924 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8323. Min Act: -0.1700

Data Index: 4556681 (Open Web Text)

Max Activating Token Index: 169

Text #6

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8193. Min Act: -0.1700

Data Index: 6327481 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7966. Min Act: -0.1700

Data Index: 2939398 (Open Web Text)

Max Activating Token Index: 153

Text #8

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8002. Min Act: -0.1685

Data Index: 3794310 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8022. Min Act: -0.1700

Data Index: 1701937 (Open Web Text)

Max Activating Token Index: 270

Text #10

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8003. Min Act: -0.1700

Data Index: 3925336 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7983. Min Act: -0.1689

Data Index: 1998140 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7982. Min Act: -0.1697

Data Index: 3794326 (Open Web Text)

Max Activating Token Index: 464

Text #13

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7957. Min Act: -0.1700

Data Index: 7502112 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.8010. Min Act: -0.1700

Data Index: 1812655 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7956. Min Act: -0.1700

Data Index: 3872286 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7931. Min Act: -0.1700

Data Index: 514237 (Open Web Text)

Max Activating Token Index: 662

Text #17

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7927. Min Act: -0.1700

Data Index: 4513170 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7813. Min Act: -0.1696

Data Index: 1589488 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.7969. Min Act: -0.1700

Data Index: 928032 (Open Web Text)

Max Activating Token Index: 934