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

Dataset: Open Web Text

Neuron 2904 in Layer 3

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: 6.1371. Min Range: -6.1371

Max Act: 6.1371. Min Act: -0.1700

Data Index: 222429 (Open Web Text)

Max Activating Token Index: 212

Text #1

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.9276. Min Act: -0.1700

Data Index: 2772882 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.9222. Min Act: -0.1700

Data Index: 8001688 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.9151. Min Act: -0.1700

Data Index: 2627467 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.8789. Min Act: -0.1700

Data Index: 8302498 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.8728. Min Act: -0.1700

Data Index: 8830405 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.8676. Min Act: -0.1700

Data Index: 2713133 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.7901. Min Act: -0.1700

Data Index: 6586556 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.8137. Min Act: -0.1700

Data Index: 5677397 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.7649. Min Act: -0.1700

Data Index: 6567673 (Open Web Text)

Max Activating Token Index: 689

Text #10

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.7586. Min Act: -0.1700

Data Index: 2462023 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.7452. Min Act: -0.1700

Data Index: 5497109 (Open Web Text)

Max Activating Token Index: 948

Text #12

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.8102. Min Act: -0.1700

Data Index: 5818733 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.7989. Min Act: -0.1700

Data Index: 2104713 (Open Web Text)

Max Activating Token Index: 687

Text #14

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.6965. Min Act: -0.1700

Data Index: 5843284 (Open Web Text)

Max Activating Token Index: 104

Text #15

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.7349. Min Act: -0.1700

Data Index: 8232412 (Open Web Text)

Max Activating Token Index: 734

Text #16

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.7067. Min Act: -0.1700

Data Index: 7875001 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.6993. Min Act: -0.1700

Data Index: 5778640 (Open Web Text)

Max Activating Token Index: 308

Text #18

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.6529. Min Act: -0.1700

Data Index: 4991822 (Open Web Text)

Max Activating Token Index: 789

Text #19

Max Range: 6.1371. Min Range: -6.1371

Max Act: 5.6615. Min Act: -0.1700

Data Index: 7295117 (Open Web Text)

Max Activating Token Index: 675