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

Dataset: Open Web Text

Neuron 1521 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: 5.6656. Min Range: -5.6656

Max Act: 5.6656. Min Act: -0.1700

Data Index: 6269914 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.5501. Min Act: -0.1700

Data Index: 5256077 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4986. Min Act: -0.1699

Data Index: 7630208 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4986. Min Act: -0.1700

Data Index: 5471142 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4986. Min Act: -0.1700

Data Index: 1598633 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4774. Min Act: -0.1700

Data Index: 5116370 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4842. Min Act: -0.1700

Data Index: 7076431 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4345. Min Act: -0.1700

Data Index: 8813978 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4305. Min Act: -0.1700

Data Index: 8621866 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4279. Min Act: -0.1700

Data Index: 7962131 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4325. Min Act: -0.1700

Data Index: 4782770 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4258. Min Act: -0.1700

Data Index: 3185751 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4124. Min Act: -0.1700

Data Index: 2184539 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4134. Min Act: -0.1700

Data Index: 2781891 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4179. Min Act: -0.1700

Data Index: 5589773 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.3817. Min Act: -0.1700

Data Index: 593025 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.3848. Min Act: -0.1700

Data Index: 7448817 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.3660. Min Act: -0.1700

Data Index: 7597528 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.3755. Min Act: -0.1699

Data Index: 5459447 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.6656. Min Range: -5.6656

Max Act: 5.4050. Min Act: -0.1700

Data Index: 4621263 (Open Web Text)

Max Activating Token Index: 5