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

Dataset: Open Web Text

Neuron 2911 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: 3.8450. Min Range: -3.8450

Max Act: 3.8450. Min Act: -0.1700

Data Index: 6286217 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.7291. Min Act: -0.1700

Data Index: 6433920 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.7185. Min Act: -0.1700

Data Index: 7254647 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6877. Min Act: -0.1700

Data Index: 7069230 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6945. Min Act: -0.1700

Data Index: 4363148 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6872. Min Act: -0.1700

Data Index: 837203 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6770. Min Act: -0.1700

Data Index: 3302847 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.7017. Min Act: -0.1700

Data Index: 6080646 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6533. Min Act: -0.1700

Data Index: 6143784 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6548. Min Act: -0.1700

Data Index: 219791 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6576. Min Act: -0.1700

Data Index: 6682139 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6483. Min Act: -0.1700

Data Index: 6490675 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6741. Min Act: -0.1700

Data Index: 6332522 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6648. Min Act: -0.1700

Data Index: 2541310 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6588. Min Act: -0.1700

Data Index: 4978412 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6754. Min Act: -0.1700

Data Index: 4839178 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6596. Min Act: -0.1700

Data Index: 4673950 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6580. Min Act: -0.1700

Data Index: 4479539 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6752. Min Act: -0.1700

Data Index: 4206438 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6777. Min Act: -0.1700

Data Index: 1989052 (Open Web Text)

Max Activating Token Index: 3