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

Dataset: Open Web Text

Neuron 367 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: 4.9171. Min Range: -4.9171

Max Act: 4.8531. Min Act: -0.1700

Data Index: 4614486 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.8123. Min Act: -0.1700

Data Index: 1202831 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.9171. Min Act: -0.1700

Data Index: 1947796 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.8822. Min Act: -0.1700

Data Index: 1030070 (Open Web Text)

Max Activating Token Index: 293

Text #4

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.8586. Min Act: -0.1700

Data Index: 2066728 (Open Web Text)

Max Activating Token Index: 351

Text #5

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7991. Min Act: -0.1700

Data Index: 519512 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.8792. Min Act: -0.1700

Data Index: 5035807 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7539. Min Act: -0.1700

Data Index: 5815103 (Open Web Text)

Max Activating Token Index: 132

Text #8

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7756. Min Act: -0.1700

Data Index: 587666 (Open Web Text)

Max Activating Token Index: 189

Text #9

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7132. Min Act: -0.1700

Data Index: 3947271 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7068. Min Act: -0.1700

Data Index: 175608 (Open Web Text)

Max Activating Token Index: 333

Text #11

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7771. Min Act: -0.1700

Data Index: 5636282 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7294. Min Act: -0.1700

Data Index: 7456305 (Open Web Text)

Max Activating Token Index: 152

Text #13

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7298. Min Act: -0.1700

Data Index: 7262833 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7847. Min Act: -0.1700

Data Index: 4685987 (Open Web Text)

Max Activating Token Index: 832

Text #15

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7066. Min Act: -0.1700

Data Index: 6156923 (Open Web Text)

Max Activating Token Index: 936

Text #16

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7596. Min Act: -0.1700

Data Index: 410892 (Open Web Text)

Max Activating Token Index: 275

Text #17

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7001. Min Act: -0.1700

Data Index: 502136 (Open Web Text)

Max Activating Token Index: 193

Text #18

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7332. Min Act: -0.1700

Data Index: 1749415 (Open Web Text)

Max Activating Token Index: 262

Text #19

Max Range: 4.9171. Min Range: -4.9171

Max Act: 4.7128. Min Act: -0.1700

Data Index: 5193357 (Open Web Text)

Max Activating Token Index: 430