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

Dataset: Open Web Text

Neuron 2561 in Layer 6

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: 3.4036. Min Range: -3.4036

Max Act: 3.4036. Min Act: -0.1700

Data Index: 4367296 (Open Web Text)

Max Activating Token Index: 1003

Text #1

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2981. Min Act: -0.1700

Data Index: 1478105 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2615. Min Act: -0.1700

Data Index: 6806909 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2499. Min Act: -0.1700

Data Index: 6050171 (Open Web Text)

Max Activating Token Index: 575

Text #4

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2485. Min Act: -0.1700

Data Index: 6348586 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2465. Min Act: -0.1700

Data Index: 4076967 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2360. Min Act: -0.1700

Data Index: 4896735 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2600. Min Act: -0.1700

Data Index: 5058245 (Open Web Text)

Max Activating Token Index: 752

Text #8

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2227. Min Act: -0.1700

Data Index: 5479183 (Open Web Text)

Max Activating Token Index: 777

Text #9

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1984. Min Act: -0.1700

Data Index: 2098581 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1901. Min Act: -0.1700

Data Index: 7052789 (Open Web Text)

Max Activating Token Index: 1001

Text #11

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2291. Min Act: -0.1700

Data Index: 2590674 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1952. Min Act: -0.1700

Data Index: 697585 (Open Web Text)

Max Activating Token Index: 230

Text #13

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1758. Min Act: -0.1700

Data Index: 7030981 (Open Web Text)

Max Activating Token Index: 724

Text #14

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1950. Min Act: -0.1700

Data Index: 6751921 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1764. Min Act: -0.1700

Data Index: 7263127 (Open Web Text)

Max Activating Token Index: 124

Text #16

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1764. Min Act: -0.1700

Data Index: 5153851 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1657. Min Act: -0.1700

Data Index: 2791131 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1380648 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.1719. Min Act: -0.1700

Data Index: 6567315 (Open Web Text)

Max Activating Token Index: 716