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

Dataset: Open Web Text

Neuron 34 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: 3.4990. Min Range: -3.4990

Max Act: 3.4990. Min Act: -0.1700

Data Index: 23193 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4624. Min Act: -0.1700

Data Index: 8176768 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4825. Min Act: -0.1700

Data Index: 7636747 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4868. Min Act: -0.1700

Data Index: 4869979 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4434. Min Act: -0.1700

Data Index: 6778629 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4478. Min Act: -0.1700

Data Index: 3787091 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4509. Min Act: -0.1700

Data Index: 5969734 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4429. Min Act: -0.1700

Data Index: 5215094 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4465. Min Act: -0.1700

Data Index: 4806212 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4136. Min Act: -0.1700

Data Index: 8703082 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4003. Min Act: -0.1700

Data Index: 5287335 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4192. Min Act: -0.1700

Data Index: 5704639 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.4140. Min Act: -0.1700

Data Index: 8216290 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.3680. Min Act: -0.1700

Data Index: 3275374 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.3883. Min Act: -0.1700

Data Index: 6575688 (Open Web Text)

Max Activating Token Index: 883

Text #15

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.3628. Min Act: -0.1700

Data Index: 6600727 (Open Web Text)

Max Activating Token Index: 112

Text #16

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.3670. Min Act: -0.1700

Data Index: 6614016 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.3819. Min Act: -0.1700

Data Index: 3939943 (Open Web Text)

Max Activating Token Index: 809

Text #18

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.3730. Min Act: -0.1700

Data Index: 2053038 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.4990. Min Range: -3.4990

Max Act: 3.3913. Min Act: -0.1700

Data Index: 4102847 (Open Web Text)

Max Activating Token Index: 35