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

Dataset: Open Web Text

Neuron 710 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: 4.7080. Min Range: -4.7080

Max Act: 4.7080. Min Act: -0.1700

Data Index: 3944908 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.6847. Min Act: -0.1700

Data Index: 4591171 (Open Web Text)

Max Activating Token Index: 934

Text #2

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.6658. Min Act: -0.1700

Data Index: 720886 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.6531. Min Act: -0.1700

Data Index: 3460785 (Open Web Text)

Max Activating Token Index: 947

Text #4

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.6093. Min Act: -0.1700

Data Index: 8320596 (Open Web Text)

Max Activating Token Index: 543

Text #5

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5946. Min Act: -0.1700

Data Index: 2071907 (Open Web Text)

Max Activating Token Index: 821

Text #6

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.6159. Min Act: -0.1700

Data Index: 1552364 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5823. Min Act: -0.1700

Data Index: 3349210 (Open Web Text)

Max Activating Token Index: 275

Text #8

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5443. Min Act: -0.1700

Data Index: 2472544 (Open Web Text)

Max Activating Token Index: 433

Text #9

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5383. Min Act: -0.1700

Data Index: 4034088 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5864. Min Act: -0.1700

Data Index: 2677758 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5501. Min Act: -0.1700

Data Index: 3706485 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5432. Min Act: -0.1700

Data Index: 3652269 (Open Web Text)

Max Activating Token Index: 907

Text #13

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5458. Min Act: -0.1700

Data Index: 8599061 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5464. Min Act: -0.1700

Data Index: 8507158 (Open Web Text)

Max Activating Token Index: 510

Text #15

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5602. Min Act: -0.1700

Data Index: 6439264 (Open Web Text)

Max Activating Token Index: 629

Text #16

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5799. Min Act: -0.1700

Data Index: 4283830 (Open Web Text)

Max Activating Token Index: 720

Text #17

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5343. Min Act: -0.1700

Data Index: 4241337 (Open Web Text)

Max Activating Token Index: 647

Text #18

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5398. Min Act: -0.1700

Data Index: 2247992 (Open Web Text)

Max Activating Token Index: 802

Text #19

Max Range: 4.7080. Min Range: -4.7080

Max Act: 4.5131. Min Act: -0.1700

Data Index: 6119424 (Open Web Text)

Max Activating Token Index: 554