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

Dataset: Open Web Text

Neuron 119 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: 4.4970. Min Range: -4.4970

Max Act: 4.4970. Min Act: -0.1700

Data Index: 147001 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4970. Min Act: -0.1700

Data Index: 6005746 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4849. Min Act: -0.1700

Data Index: 7042026 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4603. Min Act: -0.1700

Data Index: 8493122 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4562. Min Act: -0.1700

Data Index: 4334558 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4741. Min Act: -0.1700

Data Index: 4413409 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4604. Min Act: -0.1700

Data Index: 4707593 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4636. Min Act: -0.1700

Data Index: 7221078 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4397. Min Act: -0.1700

Data Index: 1787225 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4231. Min Act: -0.1700

Data Index: 6166283 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4374. Min Act: -0.1700

Data Index: 5554831 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4397. Min Act: -0.1700

Data Index: 7517593 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4212. Min Act: -0.1700

Data Index: 906491 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4399. Min Act: -0.1700

Data Index: 3268494 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4286. Min Act: -0.1700

Data Index: 3114449 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4310. Min Act: -0.1700

Data Index: 4096962 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4324. Min Act: -0.1700

Data Index: 1912992 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4372. Min Act: -0.1700

Data Index: 6213326 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.4331. Min Act: -0.1700

Data Index: 3410715 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.4970. Min Range: -4.4970

Max Act: 4.3960. Min Act: -0.1700

Data Index: 2916650 (Open Web Text)

Max Activating Token Index: 4