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

Dataset: Open Web Text

Neuron 74 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: 2.8163. Min Range: -2.8163

Max Act: 2.8163. Min Act: -0.1700

Data Index: 4863679 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.7302. Min Act: -0.1700

Data Index: 6439533 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.7125. Min Act: -0.1700

Data Index: 6362466 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.7166. Min Act: -0.1700

Data Index: 4632947 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.7028. Min Act: -0.1700

Data Index: 8451546 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6744. Min Act: -0.1700

Data Index: 2419085 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6744. Min Act: -0.1700

Data Index: 6655278 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6744. Min Act: -0.1700

Data Index: 4252553 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6705. Min Act: -0.1700

Data Index: 5748779 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6601. Min Act: -0.1700

Data Index: 5765204 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6547. Min Act: -0.1700

Data Index: 1752787 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6604. Min Act: -0.1700

Data Index: 2999561 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6547. Min Act: -0.1700

Data Index: 8422935 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6616. Min Act: -0.1700

Data Index: 1026348 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6533. Min Act: -0.1700

Data Index: 800027 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6506. Min Act: -0.1700

Data Index: 3939783 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6385. Min Act: -0.1700

Data Index: 3410552 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6486. Min Act: -0.1700

Data Index: 2887925 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6385. Min Act: -0.1700

Data Index: 4609576 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.8163. Min Range: -2.8163

Max Act: 2.6549. Min Act: -0.1700

Data Index: 5551266 (Open Web Text)

Max Activating Token Index: 7