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

Dataset: Open Web Text

Neuron 3011 in Layer 5

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: 3.2052. Min Range: -3.2052

Max Act: 3.2052. Min Act: -0.1700

Data Index: 1607908 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1707. Min Act: -0.1700

Data Index: 7981971 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1362. Min Act: -0.1700

Data Index: 4051089 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0999. Min Act: -0.1700

Data Index: 8253311 (Open Web Text)

Max Activating Token Index: 461

Text #4

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0930. Min Act: -0.1700

Data Index: 5510642 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0970. Min Act: -0.1700

Data Index: 948119 (Open Web Text)

Max Activating Token Index: 331

Text #6

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1045. Min Act: -0.1700

Data Index: 1673632 (Open Web Text)

Max Activating Token Index: 754

Text #7

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0936. Min Act: -0.1700

Data Index: 7119688 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0496. Min Act: -0.1700

Data Index: 7465865 (Open Web Text)

Max Activating Token Index: 716

Text #9

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0786. Min Act: -0.1700

Data Index: 3211887 (Open Web Text)

Max Activating Token Index: 85

Text #10

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0591. Min Act: -0.1700

Data Index: 784459 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0571. Min Act: -0.1700

Data Index: 354873 (Open Web Text)

Max Activating Token Index: 360

Text #12

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0432. Min Act: -0.1700

Data Index: 3664275 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0500. Min Act: -0.1700

Data Index: 5807859 (Open Web Text)

Max Activating Token Index: 398

Text #14

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0198. Min Act: -0.1700

Data Index: 5982816 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0068. Min Act: -0.1700

Data Index: 2601994 (Open Web Text)

Max Activating Token Index: 169

Text #16

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0083. Min Act: -0.1700

Data Index: 2690532 (Open Web Text)

Max Activating Token Index: 315

Text #17

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1852490 (Open Web Text)

Max Activating Token Index: 505

Text #18

Max Range: 3.2052. Min Range: -3.2052

Max Act: 2.9901. Min Act: -0.1700

Data Index: 4194211 (Open Web Text)

Max Activating Token Index: 227

Text #19

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0112. Min Act: -0.1700

Data Index: 4642368 (Open Web Text)

Max Activating Token Index: 909