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

Dataset: Open Web Text

Neuron 1441 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: 2.9891. Min Range: -2.9891

Max Act: 2.9891. Min Act: -0.1700

Data Index: 6867068 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9798. Min Act: -0.1700

Data Index: 4435606 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9352. Min Act: -0.1700

Data Index: 4610813 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9251. Min Act: -0.1700

Data Index: 857397 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9207. Min Act: -0.1700

Data Index: 5832412 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9184. Min Act: -0.1700

Data Index: 7673235 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9223. Min Act: -0.1700

Data Index: 3812377 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9262. Min Act: -0.1700

Data Index: 3439406 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9185. Min Act: -0.1700

Data Index: 663082 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8972. Min Act: -0.1700

Data Index: 1201256 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9060. Min Act: -0.1700

Data Index: 5272571 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8988. Min Act: -0.1700

Data Index: 6688206 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.9008. Min Act: -0.1700

Data Index: 7141996 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8853. Min Act: -0.1700

Data Index: 15458 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8832. Min Act: -0.1700

Data Index: 504672 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8791. Min Act: -0.1700

Data Index: 6688205 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8763. Min Act: -0.1700

Data Index: 5370473 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8710. Min Act: -0.1700

Data Index: 1901544 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8662. Min Act: -0.1700

Data Index: 4693468 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 2.9891. Min Range: -2.9891

Max Act: 2.8619. Min Act: -0.1700

Data Index: 1247755 (Open Web Text)

Max Activating Token Index: 361