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

Dataset: Open Web Text

Neuron 2040 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: 3.7306. Min Range: -3.7306

Max Act: 3.7306. Min Act: -0.1700

Data Index: 7525555 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.7067. Min Act: -0.1700

Data Index: 6830568 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.7155. Min Act: -0.1700

Data Index: 4331404 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6986. Min Act: -0.1700

Data Index: 1336819 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6751. Min Act: -0.1700

Data Index: 6694985 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6668. Min Act: -0.1700

Data Index: 776515 (Open Web Text)

Max Activating Token Index: 189

Text #6

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6655. Min Act: -0.1700

Data Index: 827269 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6743. Min Act: -0.1700

Data Index: 6312697 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6780. Min Act: -0.1700

Data Index: 3493503 (Open Web Text)

Max Activating Token Index: 59

Text #9

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6666. Min Act: -0.1700

Data Index: 3085127 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6604. Min Act: -0.1700

Data Index: 5477772 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6328. Min Act: -0.1700

Data Index: 5316010 (Open Web Text)

Max Activating Token Index: 53

Text #12

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6582. Min Act: -0.1700

Data Index: 4539063 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6340. Min Act: -0.1700

Data Index: 1352038 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6569. Min Act: -0.1700

Data Index: 4300731 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6530. Min Act: -0.1700

Data Index: 238373 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6532. Min Act: -0.1700

Data Index: 2339435 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6569. Min Act: -0.1700

Data Index: 3826552 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6427. Min Act: -0.1700

Data Index: 837031 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.7306. Min Range: -3.7306

Max Act: 3.6572. Min Act: -0.1700

Data Index: 3735288 (Open Web Text)

Max Activating Token Index: 11