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

Dataset: Open Web Text

Neuron 964 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: 4.0821. Min Range: -4.0821

Max Act: 4.0821. Min Act: -0.1700

Data Index: 7811410 (Open Web Text)

Max Activating Token Index: 576

Text #1

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0787. Min Act: -0.1700

Data Index: 8093683 (Open Web Text)

Max Activating Token Index: 573

Text #2

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9786. Min Act: -0.1700

Data Index: 1068831 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0138. Min Act: -0.1700

Data Index: 1591626 (Open Web Text)

Max Activating Token Index: 625

Text #4

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0062. Min Act: -0.1700

Data Index: 7867137 (Open Web Text)

Max Activating Token Index: 214

Text #5

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0296. Min Act: -0.1700

Data Index: 215385 (Open Web Text)

Max Activating Token Index: 285

Text #6

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9958. Min Act: -0.1700

Data Index: 503925 (Open Web Text)

Max Activating Token Index: 445

Text #7

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9988. Min Act: -0.1700

Data Index: 6378619 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9580. Min Act: -0.1700

Data Index: 2359863 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9796. Min Act: -0.1700

Data Index: 4124 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9821. Min Act: -0.1700

Data Index: 8045016 (Open Web Text)

Max Activating Token Index: 296

Text #11

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9729. Min Act: -0.1700

Data Index: 3191003 (Open Web Text)

Max Activating Token Index: 445

Text #12

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9767. Min Act: -0.1700

Data Index: 6630727 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9846. Min Act: -0.1700

Data Index: 6571172 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9828. Min Act: -0.1700

Data Index: 6203169 (Open Web Text)

Max Activating Token Index: 358

Text #15

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9679. Min Act: -0.1700

Data Index: 5534588 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9906. Min Act: -0.1700

Data Index: 2144666 (Open Web Text)

Max Activating Token Index: 74

Text #17

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9971. Min Act: -0.1700

Data Index: 426804 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9924. Min Act: -0.1700

Data Index: 4829152 (Open Web Text)

Max Activating Token Index: 581

Text #19

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9749. Min Act: -0.1700

Data Index: 4335235 (Open Web Text)

Max Activating Token Index: 918