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

Dataset: Open Web Text

Neuron 2313 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: 4.5747. Min Range: -4.5747

Max Act: 4.5747. Min Act: -0.1700

Data Index: 6084392 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.5138. Min Act: -0.1700

Data Index: 2405627 (Open Web Text)

Max Activating Token Index: 344

Text #2

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.5523. Min Act: -0.1700

Data Index: 6676244 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4890. Min Act: -0.1700

Data Index: 2507434 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.5003. Min Act: -0.1700

Data Index: 8638621 (Open Web Text)

Max Activating Token Index: 740

Text #5

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4619. Min Act: -0.1700

Data Index: 2950108 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4114. Min Act: -0.1700

Data Index: 4284684 (Open Web Text)

Max Activating Token Index: 406

Text #7

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4165. Min Act: -0.1700

Data Index: 7167550 (Open Web Text)

Max Activating Token Index: 441

Text #8

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4124. Min Act: -0.1700

Data Index: 7827230 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4154. Min Act: -0.1700

Data Index: 6585823 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4100. Min Act: -0.1700

Data Index: 3603518 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.3788. Min Act: -0.1700

Data Index: 4399061 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4054. Min Act: -0.1700

Data Index: 8466325 (Open Web Text)

Max Activating Token Index: 878

Text #13

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4128. Min Act: -0.1700

Data Index: 4906461 (Open Web Text)

Max Activating Token Index: 421

Text #14

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.3908. Min Act: -0.1700

Data Index: 2886827 (Open Web Text)

Max Activating Token Index: 439

Text #15

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.4080. Min Act: -0.1700

Data Index: 5271830 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.3522. Min Act: -0.1700

Data Index: 2946937 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.3736. Min Act: -0.1700

Data Index: 165565 (Open Web Text)

Max Activating Token Index: 234

Text #18

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.3501. Min Act: -0.1700

Data Index: 5133071 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 4.5747. Min Range: -4.5747

Max Act: 4.3638. Min Act: -0.1700

Data Index: 2405029 (Open Web Text)

Max Activating Token Index: 18