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

Dataset: Open Web Text

Neuron 1356 in Layer 4

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: 2.8036. Min Range: -2.8036

Max Act: 2.8036. Min Act: -0.1700

Data Index: 2734449 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7918. Min Act: -0.1700

Data Index: 707360 (Open Web Text)

Max Activating Token Index: 980

Text #2

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7628. Min Act: -0.1700

Data Index: 6464522 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7711. Min Act: -0.1700

Data Index: 5991838 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7430. Min Act: -0.1700

Data Index: 1453286 (Open Web Text)

Max Activating Token Index: 665

Text #5

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7385. Min Act: -0.1700

Data Index: 5818175 (Open Web Text)

Max Activating Token Index: 864

Text #6

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7158. Min Act: -0.1700

Data Index: 4951270 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7162. Min Act: -0.1700

Data Index: 698271 (Open Web Text)

Max Activating Token Index: 120

Text #8

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7112. Min Act: -0.1700

Data Index: 1001694 (Open Web Text)

Max Activating Token Index: 830

Text #9

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7142. Min Act: -0.1700

Data Index: 914753 (Open Web Text)

Max Activating Token Index: 892

Text #10

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7178. Min Act: -0.1700

Data Index: 4303601 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7009. Min Act: -0.1700

Data Index: 8092656 (Open Web Text)

Max Activating Token Index: 162

Text #12

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6981. Min Act: -0.1700

Data Index: 629331 (Open Web Text)

Max Activating Token Index: 820

Text #13

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6966. Min Act: -0.1700

Data Index: 8431320 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6639. Min Act: -0.1700

Data Index: 6562164 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6811. Min Act: -0.1700

Data Index: 7171377 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6699. Min Act: -0.1700

Data Index: 1546766 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6584. Min Act: -0.1700

Data Index: 5064422 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6591. Min Act: -0.1700

Data Index: 1895289 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6703. Min Act: -0.1700

Data Index: 6476872 (Open Web Text)

Max Activating Token Index: 341