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

Dataset: Open Web Text

Neuron 570 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: 4.0691. Min Range: -4.0691

Max Act: 4.0691. Min Act: -0.1700

Data Index: 7908655 (Open Web Text)

Max Activating Token Index: 651

Text #1

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.9919. Min Act: -0.1700

Data Index: 3536653 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.9455. Min Act: -0.1700

Data Index: 799358 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8704. Min Act: -0.1700

Data Index: 5817345 (Open Web Text)

Max Activating Token Index: 102

Text #4

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8918. Min Act: -0.1700

Data Index: 3011701 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.9098. Min Act: -0.1700

Data Index: 4179518 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8745. Min Act: -0.1700

Data Index: 1720066 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8904. Min Act: -0.1700

Data Index: 7088231 (Open Web Text)

Max Activating Token Index: 730

Text #8

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8227. Min Act: -0.1700

Data Index: 7716578 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8026. Min Act: -0.1700

Data Index: 1953258 (Open Web Text)

Max Activating Token Index: 584

Text #10

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7944. Min Act: -0.1700

Data Index: 1953264 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8304. Min Act: -0.1700

Data Index: 8500280 (Open Web Text)

Max Activating Token Index: 585

Text #12

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7942. Min Act: -0.1700

Data Index: 7834370 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7799. Min Act: -0.1700

Data Index: 8631717 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7183. Min Act: -0.1700

Data Index: 899363 (Open Web Text)

Max Activating Token Index: 204

Text #15

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7346. Min Act: -0.1700

Data Index: 8424392 (Open Web Text)

Max Activating Token Index: 780

Text #16

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7735. Min Act: -0.1700

Data Index: 868430 (Open Web Text)

Max Activating Token Index: 743

Text #17

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7289. Min Act: -0.1700

Data Index: 4140399 (Open Web Text)

Max Activating Token Index: 126

Text #18

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7616. Min Act: -0.1700

Data Index: 2672501 (Open Web Text)

Max Activating Token Index: 465

Text #19

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7505. Min Act: -0.1700

Data Index: 279846 (Open Web Text)

Max Activating Token Index: 190