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

Dataset: Open Web Text

Neuron 855 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: 4.9126. Min Range: -4.9126

Max Act: 4.9126. Min Act: -0.1700

Data Index: 5772566 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.8501. Min Act: -0.1700

Data Index: 3467360 (Open Web Text)

Max Activating Token Index: 500

Text #2

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.8191. Min Act: -0.1700

Data Index: 7473614 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.8098. Min Act: -0.1700

Data Index: 8273127 (Open Web Text)

Max Activating Token Index: 883

Text #4

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.8178. Min Act: -0.1700

Data Index: 203994 (Open Web Text)

Max Activating Token Index: 74

Text #5

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.8130. Min Act: -0.1700

Data Index: 6761074 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.8252. Min Act: -0.1700

Data Index: 2679819 (Open Web Text)

Max Activating Token Index: 811

Text #7

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.8113. Min Act: -0.1700

Data Index: 6731055 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7721. Min Act: -0.1700

Data Index: 541894 (Open Web Text)

Max Activating Token Index: 704

Text #9

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7814. Min Act: -0.1700

Data Index: 1495717 (Open Web Text)

Max Activating Token Index: 176

Text #10

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7878. Min Act: -0.1700

Data Index: 6320022 (Open Web Text)

Max Activating Token Index: 38

Text #11

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7950. Min Act: -0.1700

Data Index: 2109846 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7610. Min Act: -0.1700

Data Index: 2078628 (Open Web Text)

Max Activating Token Index: 269

Text #13

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7748. Min Act: -0.1700

Data Index: 5576602 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7823. Min Act: -0.1700

Data Index: 5413766 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7533. Min Act: -0.1700

Data Index: 88998 (Open Web Text)

Max Activating Token Index: 290

Text #16

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7378. Min Act: -0.1700

Data Index: 561979 (Open Web Text)

Max Activating Token Index: 526

Text #17

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7467. Min Act: -0.1700

Data Index: 3434856 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7666. Min Act: -0.1700

Data Index: 1995104 (Open Web Text)

Max Activating Token Index: 182

Text #19

Max Range: 4.9126. Min Range: -4.9126

Max Act: 4.7700. Min Act: -0.1700

Data Index: 4298354 (Open Web Text)

Max Activating Token Index: 269