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

Dataset: Open Web Text

Neuron 2145 in Layer 5

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: 6.0838. Min Range: -6.0838

Max Act: 6.0838. Min Act: -0.1700

Data Index: 8437777 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.6171. Min Act: -0.1700

Data Index: 2232519 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.5884. Min Act: -0.1700

Data Index: 749593 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.5003. Min Act: -0.1700

Data Index: 7709786 (Open Web Text)

Max Activating Token Index: 97

Text #4

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.5483. Min Act: -0.1700

Data Index: 204724 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.4932. Min Act: -0.1700

Data Index: 7849604 (Open Web Text)

Max Activating Token Index: 971

Text #6

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.4478. Min Act: -0.1700

Data Index: 7738521 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.4896. Min Act: -0.1700

Data Index: 6710921 (Open Web Text)

Max Activating Token Index: 425

Text #8

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.5108. Min Act: -0.1700

Data Index: 3754468 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.4806. Min Act: -0.1700

Data Index: 7881496 (Open Web Text)

Max Activating Token Index: 922

Text #10

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.4435. Min Act: -0.1700

Data Index: 6337527 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.4433. Min Act: -0.1700

Data Index: 421556 (Open Web Text)

Max Activating Token Index: 320

Text #12

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.4368. Min Act: -0.1700

Data Index: 4325991 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.3805. Min Act: -0.1700

Data Index: 2388448 (Open Web Text)

Max Activating Token Index: 968

Text #14

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.3695. Min Act: -0.1700

Data Index: 6212679 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.3812. Min Act: -0.1700

Data Index: 1986677 (Open Web Text)

Max Activating Token Index: 1015

Text #16

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.3790. Min Act: -0.1700

Data Index: 8053088 (Open Web Text)

Max Activating Token Index: 978

Text #17

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.2937. Min Act: -0.1700

Data Index: 1258101 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.3221. Min Act: -0.1700

Data Index: 6094625 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 6.0838. Min Range: -6.0838

Max Act: 5.2997. Min Act: -0.1700

Data Index: 3045005 (Open Web Text)

Max Activating Token Index: 459