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

Dataset: Open Web Text

Neuron 2904 in Layer 6

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: 3.5634. Min Range: -3.5634

Max Act: 3.5451. Min Act: -0.1700

Data Index: 4951420 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.5634. Min Act: -0.1700

Data Index: 5466669 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.5207. Min Act: -0.1700

Data Index: 891304 (Open Web Text)

Max Activating Token Index: 144

Text #3

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.5130. Min Act: -0.1700

Data Index: 554826 (Open Web Text)

Max Activating Token Index: 60

Text #4

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4692. Min Act: -0.1700

Data Index: 3582002 (Open Web Text)

Max Activating Token Index: 196

Text #5

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4815. Min Act: -0.1700

Data Index: 1223956 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4150. Min Act: -0.1700

Data Index: 5647051 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4599. Min Act: -0.1700

Data Index: 1840366 (Open Web Text)

Max Activating Token Index: 509

Text #8

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4458. Min Act: -0.1700

Data Index: 4710128 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4531. Min Act: -0.1700

Data Index: 5361771 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4206. Min Act: -0.1700

Data Index: 8434214 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4139. Min Act: -0.1700

Data Index: 8816963 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4010. Min Act: -0.1700

Data Index: 6038666 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3954. Min Act: -0.1700

Data Index: 8096591 (Open Web Text)

Max Activating Token Index: 432

Text #14

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4008. Min Act: -0.1700

Data Index: 5085188 (Open Web Text)

Max Activating Token Index: 793

Text #15

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4015. Min Act: -0.1700

Data Index: 3665345 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3454. Min Act: -0.1700

Data Index: 2311946 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3898. Min Act: -0.1700

Data Index: 6417319 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.4019. Min Act: -0.1700

Data Index: 4497687 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1599928 (Open Web Text)

Max Activating Token Index: 197