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

Dataset: Open Web Text

Neuron 141 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: 3.0301. Min Range: -3.0301

Max Act: 3.0301. Min Act: -0.1699

Data Index: 8143226 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 3.0301. Min Range: -3.0301

Max Act: 3.0186. Min Act: -0.1700

Data Index: 8143227 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 3.0301. Min Range: -3.0301

Max Act: 3.0203. Min Act: -0.1638

Data Index: 393340 (Open Web Text)

Max Activating Token Index: 391

Text #3

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9753. Min Act: -0.1700

Data Index: 7469507 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9800. Min Act: -0.1700

Data Index: 8806817 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9646. Min Act: -0.1700

Data Index: 5900232 (Open Web Text)

Max Activating Token Index: 81

Text #6

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9535. Min Act: -0.1700

Data Index: 4314144 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9240. Min Act: -0.1700

Data Index: 7718916 (Open Web Text)

Max Activating Token Index: 326

Text #8

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9311. Min Act: -0.1700

Data Index: 2115819 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9398. Min Act: -0.1700

Data Index: 6695612 (Open Web Text)

Max Activating Token Index: 572

Text #10

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9182. Min Act: -0.1700

Data Index: 7419607 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9154. Min Act: -0.1700

Data Index: 5250914 (Open Web Text)

Max Activating Token Index: 198

Text #12

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9164. Min Act: -0.1699

Data Index: 2407036 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9066. Min Act: -0.1700

Data Index: 7059305 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8997. Min Act: -0.1700

Data Index: 8255577 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.9117. Min Act: -0.1700

Data Index: 7718917 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8915. Min Act: -0.1700

Data Index: 3079248 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8909. Min Act: -0.1696

Data Index: 5454292 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8903. Min Act: -0.1700

Data Index: 2128135 (Open Web Text)

Max Activating Token Index: 166

Text #19

Max Range: 3.0301. Min Range: -3.0301

Max Act: 2.8946. Min Act: -0.1700

Data Index: 4114155 (Open Web Text)

Max Activating Token Index: 95