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

Dataset: Open Web Text

Neuron 2887 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: 3.5962. Min Range: -3.5962

Max Act: 3.5962. Min Act: -0.1700

Data Index: 8599581 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5962. Min Act: -0.1700

Data Index: 2706461 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5602. Min Act: -0.1700

Data Index: 1374380 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5229. Min Act: -0.1700

Data Index: 8253496 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5312. Min Act: -0.1700

Data Index: 6273747 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4983. Min Act: -0.1699

Data Index: 8019383 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4962. Min Act: -0.1700

Data Index: 7592360 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4962. Min Act: -0.1700

Data Index: 3728959 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4957. Min Act: -0.1700

Data Index: 8661132 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5161. Min Act: -0.1699

Data Index: 1053452 (Open Web Text)

Max Activating Token Index: 27

Text #10

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5161. Min Act: -0.1699

Data Index: 7458427 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4722. Min Act: -0.1700

Data Index: 1489895 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4564. Min Act: -0.1700

Data Index: 6445249 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4771. Min Act: -0.1700

Data Index: 4845096 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4806. Min Act: -0.1700

Data Index: 4447942 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4771. Min Act: -0.1700

Data Index: 8426628 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4810. Min Act: -0.1699

Data Index: 8810835 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4601. Min Act: -0.1697

Data Index: 3378240 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4810. Min Act: -0.1700

Data Index: 8365066 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4223. Min Act: -0.1700

Data Index: 7350177 (Open Web Text)

Max Activating Token Index: 15