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

Dataset: Open Web Text

Neuron 2153 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: 3.7012. Min Range: -3.7012

Max Act: 3.7012. Min Act: -0.1700

Data Index: 4966409 (Open Web Text)

Max Activating Token Index: 601

Text #1

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.6808. Min Act: -0.1700

Data Index: 2177154 (Open Web Text)

Max Activating Token Index: 115

Text #2

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.6220. Min Act: -0.1700

Data Index: 7275285 (Open Web Text)

Max Activating Token Index: 387

Text #3

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5913. Min Act: -0.1700

Data Index: 3221120 (Open Web Text)

Max Activating Token Index: 665

Text #4

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5773. Min Act: -0.1700

Data Index: 8633978 (Open Web Text)

Max Activating Token Index: 424

Text #5

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5508. Min Act: -0.1700

Data Index: 8550659 (Open Web Text)

Max Activating Token Index: 303

Text #6

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5488. Min Act: -0.1700

Data Index: 6512022 (Open Web Text)

Max Activating Token Index: 137

Text #7

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5446. Min Act: -0.1700

Data Index: 6872548 (Open Web Text)

Max Activating Token Index: 481

Text #8

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5372. Min Act: -0.1700

Data Index: 4640245 (Open Web Text)

Max Activating Token Index: 296

Text #9

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5125. Min Act: -0.1700

Data Index: 1409490 (Open Web Text)

Max Activating Token Index: 196

Text #10

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5003. Min Act: -0.1700

Data Index: 3264706 (Open Web Text)

Max Activating Token Index: 1013

Text #11

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4996. Min Act: -0.1700

Data Index: 1472162 (Open Web Text)

Max Activating Token Index: 845

Text #12

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.5050. Min Act: -0.1700

Data Index: 5270341 (Open Web Text)

Max Activating Token Index: 902

Text #13

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4911. Min Act: -0.1700

Data Index: 2792590 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4945. Min Act: -0.1700

Data Index: 133597 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4736. Min Act: -0.1700

Data Index: 6512020 (Open Web Text)

Max Activating Token Index: 804

Text #16

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4652. Min Act: -0.1700

Data Index: 1266448 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4721. Min Act: -0.1700

Data Index: 6512015 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4659. Min Act: -0.1700

Data Index: 2792588 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 3.7012. Min Range: -3.7012

Max Act: 3.4777. Min Act: -0.1700

Data Index: 6605439 (Open Web Text)

Max Activating Token Index: 633