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

Dataset: Open Web Text

Neuron 2500 in Layer 0

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: 4.0937. Min Range: -4.0937

Max Act: 4.0937. Min Act: -0.1700

Data Index: 3732597 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.0937. Min Range: -4.0937

Max Act: 4.0481. Min Act: -0.1700

Data Index: 5003621 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 4.0937. Min Range: -4.0937

Max Act: 4.0009. Min Act: -0.1700

Data Index: 2711951 (Open Web Text)

Max Activating Token Index: 831

Text #3

Max Range: 4.0937. Min Range: -4.0937

Max Act: 4.0208. Min Act: -0.1700

Data Index: 6528725 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0937. Min Range: -4.0937

Max Act: 4.0037. Min Act: -0.1700

Data Index: 7891157 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 4.0937. Min Range: -4.0937

Max Act: 4.0091. Min Act: -0.1700

Data Index: 3423590 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 4.0937. Min Range: -4.0937

Max Act: 4.0020. Min Act: -0.1700

Data Index: 4130225 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9848. Min Act: -0.1700

Data Index: 5941836 (Open Web Text)

Max Activating Token Index: 841

Text #8

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9835. Min Act: -0.1700

Data Index: 5337826 (Open Web Text)

Max Activating Token Index: 946

Text #9

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9661. Min Act: -0.1700

Data Index: 7494968 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9627. Min Act: -0.1700

Data Index: 4714759 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9746. Min Act: -0.1700

Data Index: 193771 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9783. Min Act: -0.1700

Data Index: 7306264 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9785. Min Act: -0.1700

Data Index: 6819710 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9720. Min Act: -0.1700

Data Index: 1807898 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9864. Min Act: -0.1700

Data Index: 361021 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9812. Min Act: -0.1700

Data Index: 2811508 (Open Web Text)

Max Activating Token Index: 60

Text #17

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9426. Min Act: -0.1700

Data Index: 2596238 (Open Web Text)

Max Activating Token Index: 365

Text #18

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9369. Min Act: -0.1700

Data Index: 5365703 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0937. Min Range: -4.0937

Max Act: 3.9548. Min Act: -0.1700

Data Index: 2728078 (Open Web Text)

Max Activating Token Index: 920