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

Dataset: Open Web Text

Neuron 2547 in Layer 3

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: 5.4107. Min Range: -5.4107

Max Act: 5.4107. Min Act: -0.1700

Data Index: 6380141 (Open Web Text)

Max Activating Token Index: 573

Text #1

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.3785. Min Act: -0.1700

Data Index: 1075117 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.3092. Min Act: -0.1700

Data Index: 7619962 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2334. Min Act: -0.1700

Data Index: 1270550 (Open Web Text)

Max Activating Token Index: 594

Text #4

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2623. Min Act: -0.1700

Data Index: 5118043 (Open Web Text)

Max Activating Token Index: 940

Text #5

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2492. Min Act: -0.1700

Data Index: 8127092 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2368. Min Act: -0.1700

Data Index: 4510737 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2468. Min Act: -0.1700

Data Index: 6015096 (Open Web Text)

Max Activating Token Index: 291

Text #8

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2808. Min Act: -0.1700

Data Index: 5873201 (Open Web Text)

Max Activating Token Index: 546

Text #9

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2170. Min Act: -0.1700

Data Index: 5012838 (Open Web Text)

Max Activating Token Index: 592

Text #10

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2565. Min Act: -0.1700

Data Index: 1472001 (Open Web Text)

Max Activating Token Index: 681

Text #11

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2084. Min Act: -0.1700

Data Index: 5296500 (Open Web Text)

Max Activating Token Index: 432

Text #12

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.1983. Min Act: -0.1700

Data Index: 5472389 (Open Web Text)

Max Activating Token Index: 282

Text #13

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2071. Min Act: -0.1700

Data Index: 6102521 (Open Web Text)

Max Activating Token Index: 895

Text #14

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2276. Min Act: -0.1700

Data Index: 7890212 (Open Web Text)

Max Activating Token Index: 414

Text #15

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.1956. Min Act: -0.1700

Data Index: 709515 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.2187. Min Act: -0.1700

Data Index: 1901674 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.1919. Min Act: -0.1700

Data Index: 1180198 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.1857. Min Act: -0.1700

Data Index: 4088428 (Open Web Text)

Max Activating Token Index: 310

Text #19

Max Range: 5.4107. Min Range: -5.4107

Max Act: 5.1751. Min Act: -0.1700

Data Index: 1306342 (Open Web Text)

Max Activating Token Index: 556