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

Dataset: Open Web Text

Neuron 2585 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: 4.1068. Min Range: -4.1068

Max Act: 4.1068. Min Act: -0.1700

Data Index: 7674197 (Open Web Text)

Max Activating Token Index: 760

Text #1

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0872. Min Act: -0.1700

Data Index: 6126579 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0843. Min Act: -0.1700

Data Index: 2307271 (Open Web Text)

Max Activating Token Index: 202

Text #3

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0770. Min Act: -0.1700

Data Index: 1361615 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0518. Min Act: -0.1700

Data Index: 4519788 (Open Web Text)

Max Activating Token Index: 567

Text #5

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0770. Min Act: -0.1700

Data Index: 3867953 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0565. Min Act: -0.1700

Data Index: 4954605 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0340. Min Act: -0.1700

Data Index: 2878320 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0252. Min Act: -0.1700

Data Index: 2450845 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0302. Min Act: -0.1700

Data Index: 8478036 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0388. Min Act: -0.1700

Data Index: 8005811 (Open Web Text)

Max Activating Token Index: 468

Text #11

Max Range: 4.1068. Min Range: -4.1068

Max Act: 3.9802. Min Act: -0.1700

Data Index: 7889485 (Open Web Text)

Max Activating Token Index: 404

Text #12

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0128. Min Act: -0.1700

Data Index: 5255308 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 4.1068. Min Range: -4.1068

Max Act: 3.9827. Min Act: -0.1700

Data Index: 1474357 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0126. Min Act: -0.1700

Data Index: 4156778 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0203. Min Act: -0.1700

Data Index: 7857941 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 4.1068. Min Range: -4.1068

Max Act: 3.9912. Min Act: -0.1700

Data Index: 2016003 (Open Web Text)

Max Activating Token Index: 982

Text #17

Max Range: 4.1068. Min Range: -4.1068

Max Act: 3.9925. Min Act: -0.1700

Data Index: 1889481 (Open Web Text)

Max Activating Token Index: 990

Text #18

Max Range: 4.1068. Min Range: -4.1068

Max Act: 4.0146. Min Act: -0.1700

Data Index: 4471529 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 4.1068. Min Range: -4.1068

Max Act: 3.9687. Min Act: -0.1700

Data Index: 4028165 (Open Web Text)

Max Activating Token Index: 909