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

Dataset: Open Web Text

Neuron 2765 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: 4.9881. Min Range: -4.9881

Max Act: 4.9881. Min Act: -0.1700

Data Index: 2948222 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.9316. Min Act: -0.1700

Data Index: 6581524 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.9323. Min Act: -0.1700

Data Index: 899002 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8989. Min Act: -0.1700

Data Index: 8782604 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8896. Min Act: -0.1700

Data Index: 156452 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8795. Min Act: -0.1700

Data Index: 1052359 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8500. Min Act: -0.1700

Data Index: 2373476 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8595. Min Act: -0.1700

Data Index: 453395 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8416. Min Act: -0.1700

Data Index: 98677 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8267. Min Act: -0.1700

Data Index: 6978605 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8468. Min Act: -0.1700

Data Index: 836344 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8492. Min Act: -0.1700

Data Index: 2663805 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8397. Min Act: -0.1700

Data Index: 8452387 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8211. Min Act: -0.1700

Data Index: 5888109 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8084. Min Act: -0.1700

Data Index: 1590383 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8007. Min Act: -0.1700

Data Index: 608836 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.7940. Min Act: -0.1700

Data Index: 5550880 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8140. Min Act: -0.1700

Data Index: 7471548 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8004. Min Act: -0.1700

Data Index: 7850893 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.9881. Min Range: -4.9881

Max Act: 4.8006. Min Act: -0.1700

Data Index: 7980307 (Open Web Text)

Max Activating Token Index: 10