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

Dataset: Open Web Text

Neuron 877 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: 4.0920. Min Range: -4.0920

Max Act: 4.0920. Min Act: -0.1700

Data Index: 6345151 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.0920. Min Range: -4.0920

Max Act: 4.0880. Min Act: -0.1700

Data Index: 7048620 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0920. Min Range: -4.0920

Max Act: 4.0915. Min Act: -0.1700

Data Index: 2486972 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0920. Min Range: -4.0920

Max Act: 4.0589. Min Act: -0.1700

Data Index: 2645128 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0920. Min Range: -4.0920

Max Act: 4.0484. Min Act: -0.1700

Data Index: 7712298 (Open Web Text)

Max Activating Token Index: 287

Text #5

Max Range: 4.0920. Min Range: -4.0920

Max Act: 4.0109. Min Act: -0.1700

Data Index: 4376149 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9502. Min Act: -0.1700

Data Index: 206489 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9943. Min Act: -0.1700

Data Index: 6213807 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9718. Min Act: -0.1700

Data Index: 1542771 (Open Web Text)

Max Activating Token Index: 178

Text #9

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9813. Min Act: -0.1700

Data Index: 8006136 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9723. Min Act: -0.1700

Data Index: 2697074 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9447. Min Act: -0.1700

Data Index: 7951989 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9468. Min Act: -0.1700

Data Index: 541118 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9742. Min Act: -0.1700

Data Index: 5904309 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9508. Min Act: -0.1700

Data Index: 5292739 (Open Web Text)

Max Activating Token Index: 613

Text #15

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9331. Min Act: -0.1700

Data Index: 4335068 (Open Web Text)

Max Activating Token Index: 210

Text #16

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9192. Min Act: -0.1700

Data Index: 448555 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.8894. Min Act: -0.1700

Data Index: 1791234 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9003. Min Act: -0.1700

Data Index: 4472639 (Open Web Text)

Max Activating Token Index: 220

Text #19

Max Range: 4.0920. Min Range: -4.0920

Max Act: 3.9130. Min Act: -0.1700

Data Index: 4810485 (Open Web Text)

Max Activating Token Index: 25