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

Dataset: Open Web Text

Neuron 2230 in Layer 1

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: 4.3276. Min Range: -4.3276

Max Act: 4.3276. Min Act: -0.1700

Data Index: 1706876 (Open Web Text)

Max Activating Token Index: 294

Text #1

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.2792. Min Act: -0.1700

Data Index: 681241 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.2880. Min Act: -0.1700

Data Index: 7096363 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.2773. Min Act: -0.1700

Data Index: 5263686 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1965. Min Act: -0.1700

Data Index: 5158803 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1954. Min Act: -0.1700

Data Index: 6423343 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1652. Min Act: -0.1700

Data Index: 591404 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1511. Min Act: -0.1700

Data Index: 2161972 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1303. Min Act: -0.1700

Data Index: 2356315 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1123. Min Act: -0.1700

Data Index: 5379435 (Open Web Text)

Max Activating Token Index: 185

Text #10

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1405. Min Act: -0.1700

Data Index: 607614 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1074. Min Act: -0.1700

Data Index: 8659439 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.0857. Min Act: -0.1700

Data Index: 5314955 (Open Web Text)

Max Activating Token Index: 433

Text #13

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.0898. Min Act: -0.1700

Data Index: 1853936 (Open Web Text)

Max Activating Token Index: 343

Text #14

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1051. Min Act: -0.1700

Data Index: 169759 (Open Web Text)

Max Activating Token Index: 935

Text #15

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1054. Min Act: -0.1700

Data Index: 7040743 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.1049. Min Act: -0.1700

Data Index: 1767761 (Open Web Text)

Max Activating Token Index: 373

Text #17

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.0920. Min Act: -0.1700

Data Index: 5474103 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.0660. Min Act: -0.1700

Data Index: 4982607 (Open Web Text)

Max Activating Token Index: 524

Text #19

Max Range: 4.3276. Min Range: -4.3276

Max Act: 4.0379. Min Act: -0.1700

Data Index: 2660218 (Open Web Text)

Max Activating Token Index: 163