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

Dataset: Open Web Text

Neuron 2904 in Layer 2

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: 3.8774. Min Range: -3.8774

Max Act: 3.8767. Min Act: -0.1700

Data Index: 4353191 (Open Web Text)

Max Activating Token Index: 329

Text #1

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.8774. Min Act: -0.1700

Data Index: 2035807 (Open Web Text)

Max Activating Token Index: 697

Text #2

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.8311. Min Act: -0.1700

Data Index: 5729740 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7804. Min Act: -0.1700

Data Index: 6750695 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7853. Min Act: -0.1700

Data Index: 3070909 (Open Web Text)

Max Activating Token Index: 245

Text #5

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7543. Min Act: -0.1700

Data Index: 1266806 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7383. Min Act: -0.1700

Data Index: 6167949 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7292. Min Act: -0.1700

Data Index: 7644708 (Open Web Text)

Max Activating Token Index: 247

Text #8

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7331. Min Act: -0.1700

Data Index: 5579720 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7075. Min Act: -0.1700

Data Index: 3665867 (Open Web Text)

Max Activating Token Index: 860

Text #10

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7189. Min Act: -0.1700

Data Index: 6145924 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7180. Min Act: -0.1700

Data Index: 1292568 (Open Web Text)

Max Activating Token Index: 115

Text #12

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7088. Min Act: -0.1700

Data Index: 4843607 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6923. Min Act: -0.1700

Data Index: 8452126 (Open Web Text)

Max Activating Token Index: 412

Text #14

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6520. Min Act: -0.1700

Data Index: 1321888 (Open Web Text)

Max Activating Token Index: 360

Text #15

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6660. Min Act: -0.1700

Data Index: 5275096 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6699. Min Act: -0.1700

Data Index: 2035808 (Open Web Text)

Max Activating Token Index: 161

Text #17

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6882. Min Act: -0.1700

Data Index: 5086572 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6907. Min Act: -0.1700

Data Index: 1505330 (Open Web Text)

Max Activating Token Index: 435

Text #19

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6657. Min Act: -0.1700

Data Index: 952496 (Open Web Text)

Max Activating Token Index: 488