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

Dataset: Open Web Text

Neuron 1080 in Layer 4

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: 3.8060. Min Range: -3.8060

Max Act: 3.8060. Min Act: -0.1700

Data Index: 5018752 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7866. Min Act: -0.1700

Data Index: 1662285 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7205. Min Act: -0.1700

Data Index: 1917586 (Open Web Text)

Max Activating Token Index: 898

Text #3

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6647. Min Act: -0.1700

Data Index: 8554503 (Open Web Text)

Max Activating Token Index: 961

Text #4

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6432. Min Act: -0.1700

Data Index: 2106902 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6038. Min Act: -0.1700

Data Index: 2988720 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6076. Min Act: -0.1700

Data Index: 5538878 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6040. Min Act: -0.1700

Data Index: 5455887 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1216344 (Open Web Text)

Max Activating Token Index: 463

Text #9

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6034. Min Act: -0.1700

Data Index: 8396085 (Open Web Text)

Max Activating Token Index: 280

Text #10

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6120. Min Act: -0.1700

Data Index: 5610710 (Open Web Text)

Max Activating Token Index: 489

Text #11

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5792. Min Act: -0.1700

Data Index: 280094 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5765. Min Act: -0.1700

Data Index: 5527829 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5667. Min Act: -0.1700

Data Index: 2363666 (Open Web Text)

Max Activating Token Index: 369

Text #14

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5569. Min Act: -0.1700

Data Index: 5278295 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5650. Min Act: -0.1700

Data Index: 4097550 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5757. Min Act: -0.1700

Data Index: 6507422 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5598. Min Act: -0.1700

Data Index: 3054557 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5391. Min Act: -0.1700

Data Index: 1250910 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.5521. Min Act: -0.1700

Data Index: 4209352 (Open Web Text)

Max Activating Token Index: 360