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

Dataset: Open Web Text

Neuron 1857 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: 4.2837. Min Range: -4.2837

Max Act: 4.2837. Min Act: -0.1700

Data Index: 3727026 (Open Web Text)

Max Activating Token Index: 212

Text #1

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.2009. Min Act: -0.1700

Data Index: 1503039 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.2077. Min Act: -0.1700

Data Index: 8255534 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.2079. Min Act: -0.1700

Data Index: 5361537 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.2110. Min Act: -0.1700

Data Index: 6034939 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1665. Min Act: -0.1700

Data Index: 2626206 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1787. Min Act: -0.1700

Data Index: 5663546 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1673. Min Act: -0.1700

Data Index: 7029876 (Open Web Text)

Max Activating Token Index: 566

Text #8

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1785. Min Act: -0.1700

Data Index: 6374275 (Open Web Text)

Max Activating Token Index: 215

Text #9

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1622. Min Act: -0.1700

Data Index: 966944 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1418. Min Act: -0.1700

Data Index: 1875916 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1220. Min Act: -0.1700

Data Index: 3799128 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1242. Min Act: -0.1700

Data Index: 268184 (Open Web Text)

Max Activating Token Index: 228

Text #13

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.0923. Min Act: -0.1700

Data Index: 4855031 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1062. Min Act: -0.1700

Data Index: 6493801 (Open Web Text)

Max Activating Token Index: 687

Text #15

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1107. Min Act: -0.1700

Data Index: 5055120 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1167. Min Act: -0.1700

Data Index: 6406755 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.0837. Min Act: -0.1700

Data Index: 3794259 (Open Web Text)

Max Activating Token Index: 81

Text #18

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.0983. Min Act: -0.1700

Data Index: 6425017 (Open Web Text)

Max Activating Token Index: 256

Text #19

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.1036. Min Act: -0.1700

Data Index: 1347573 (Open Web Text)

Max Activating Token Index: 168