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

Dataset: Open Web Text

Neuron 749 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: 3.1346. Min Range: -3.1346

Max Act: 3.1335. Min Act: -0.1700

Data Index: 3937631 (Open Web Text)

Max Activating Token Index: 879

Text #1

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.1346. Min Act: -0.1700

Data Index: 2742964 (Open Web Text)

Max Activating Token Index: 96

Text #2

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.1119. Min Act: -0.1700

Data Index: 6550223 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.1012. Min Act: -0.1700

Data Index: 5617355 (Open Web Text)

Max Activating Token Index: 405

Text #4

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0656. Min Act: -0.1700

Data Index: 1041079 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0342. Min Act: -0.1700

Data Index: 1393044 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0465. Min Act: -0.1700

Data Index: 6772391 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0377. Min Act: -0.1700

Data Index: 6236684 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0072. Min Act: -0.1700

Data Index: 3716293 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0005. Min Act: -0.1700

Data Index: 276477 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9959. Min Act: -0.1700

Data Index: 2040853 (Open Web Text)

Max Activating Token Index: 110

Text #11

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0288. Min Act: -0.1700

Data Index: 6619082 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0069. Min Act: -0.1700

Data Index: 8829164 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0140. Min Act: -0.1700

Data Index: 6555116 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0136. Min Act: -0.1700

Data Index: 2827396 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0008. Min Act: -0.1700

Data Index: 444783 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0031. Min Act: -0.1700

Data Index: 687783 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9983. Min Act: -0.1700

Data Index: 1056344 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0173. Min Act: -0.1700

Data Index: 4972790 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0093. Min Act: -0.1700

Data Index: 4749857 (Open Web Text)

Max Activating Token Index: 428