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

Dataset: Open Web Text

Neuron 1854 in Layer 2

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: 3.7777. Min Range: -3.7777

Max Act: 3.7777. Min Act: -0.1700

Data Index: 8247356 (Open Web Text)

Max Activating Token Index: 221

Text #1

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.7451. Min Act: -0.1700

Data Index: 1804776 (Open Web Text)

Max Activating Token Index: 885

Text #2

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1665160 (Open Web Text)

Max Activating Token Index: 660

Text #3

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.7414. Min Act: -0.1700

Data Index: 2063941 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.7122. Min Act: -0.1700

Data Index: 8693186 (Open Web Text)

Max Activating Token Index: 558

Text #5

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6816. Min Act: -0.1700

Data Index: 774748 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6637. Min Act: -0.1700

Data Index: 1086534 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6671. Min Act: -0.1700

Data Index: 6845114 (Open Web Text)

Max Activating Token Index: 538

Text #8

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6664. Min Act: -0.1700

Data Index: 3969939 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6548. Min Act: -0.1700

Data Index: 4450995 (Open Web Text)

Max Activating Token Index: 1020

Text #10

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6506. Min Act: -0.1700

Data Index: 6173279 (Open Web Text)

Max Activating Token Index: 749

Text #11

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6585. Min Act: -0.1700

Data Index: 4408690 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1983999 (Open Web Text)

Max Activating Token Index: 874

Text #13

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6469. Min Act: -0.1700

Data Index: 1731044 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6460. Min Act: -0.1700

Data Index: 4676114 (Open Web Text)

Max Activating Token Index: 731

Text #15

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6581. Min Act: -0.1700

Data Index: 1236903 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6338. Min Act: -0.1700

Data Index: 1714911 (Open Web Text)

Max Activating Token Index: 938

Text #17

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6028. Min Act: -0.1700

Data Index: 4135382 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6415. Min Act: -0.1700

Data Index: 2327747 (Open Web Text)

Max Activating Token Index: 339

Text #19

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6123. Min Act: -0.1700

Data Index: 5244888 (Open Web Text)

Max Activating Token Index: 526