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

Dataset: Open Web Text

Neuron 1237 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: 3.0174. Min Range: -3.0174

Max Act: 2.9624. Min Act: -0.1700

Data Index: 8566794 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 3.0174. Min Range: -3.0174

Max Act: 3.0174. Min Act: -0.1700

Data Index: 6170251 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.9453. Min Act: -0.1700

Data Index: 7601972 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.9300. Min Act: -0.1700

Data Index: 6993123 (Open Web Text)

Max Activating Token Index: 921

Text #4

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.9157. Min Act: -0.1700

Data Index: 1456875 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.9108. Min Act: -0.1700

Data Index: 78292 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8879. Min Act: -0.1700

Data Index: 887934 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8879. Min Act: -0.1700

Data Index: 881319 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8879. Min Act: -0.1700

Data Index: 4736068 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8879. Min Act: -0.1700

Data Index: 5582949 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8971. Min Act: -0.1700

Data Index: 6625500 (Open Web Text)

Max Activating Token Index: 871

Text #11

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8879. Min Act: -0.1700

Data Index: 6800986 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8614. Min Act: -0.1700

Data Index: 4025349 (Open Web Text)

Max Activating Token Index: 821

Text #13

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8328. Min Act: -0.1700

Data Index: 821890 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8678. Min Act: -0.1700

Data Index: 3406067 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8385. Min Act: -0.1700

Data Index: 6557846 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8684. Min Act: -0.1700

Data Index: 5331440 (Open Web Text)

Max Activating Token Index: 351

Text #17

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.8193. Min Act: -0.1700

Data Index: 4161945 (Open Web Text)

Max Activating Token Index: 409

Text #18

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.7879. Min Act: -0.1700

Data Index: 6120837 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 3.0174. Min Range: -3.0174

Max Act: 2.7834. Min Act: -0.1700

Data Index: 4143903 (Open Web Text)

Max Activating Token Index: 991