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

Dataset: Open Web Text

Neuron 1085 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: 4.4640. Min Range: -4.4640

Max Act: 4.4640. Min Act: -0.1700

Data Index: 1356592 (Open Web Text)

Max Activating Token Index: 489

Text #1

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4532. Min Act: -0.1700

Data Index: 8184432 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4525. Min Act: -0.1700

Data Index: 2099773 (Open Web Text)

Max Activating Token Index: 600

Text #3

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4395. Min Act: -0.1700

Data Index: 4837792 (Open Web Text)

Max Activating Token Index: 620

Text #4

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4161. Min Act: -0.1700

Data Index: 7972559 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4474. Min Act: -0.1700

Data Index: 7782488 (Open Web Text)

Max Activating Token Index: 380

Text #6

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4439. Min Act: -0.1700

Data Index: 3864954 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4196. Min Act: -0.1700

Data Index: 3515425 (Open Web Text)

Max Activating Token Index: 485

Text #8

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.3988. Min Act: -0.1700

Data Index: 1360501 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4107. Min Act: -0.1700

Data Index: 8157489 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.3962. Min Act: -0.1700

Data Index: 7383309 (Open Web Text)

Max Activating Token Index: 270

Text #11

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.3903. Min Act: -0.1700

Data Index: 6941153 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.3936. Min Act: -0.1700

Data Index: 4499425 (Open Web Text)

Max Activating Token Index: 245

Text #13

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4053. Min Act: -0.1700

Data Index: 6425209 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4274. Min Act: -0.1700

Data Index: 483762 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4095. Min Act: -0.1700

Data Index: 2759554 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.3925. Min Act: -0.1700

Data Index: 2656365 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.4034. Min Act: -0.1700

Data Index: 5571673 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.3991. Min Act: -0.1700

Data Index: 5356962 (Open Web Text)

Max Activating Token Index: 524

Text #19

Max Range: 4.4640. Min Range: -4.4640

Max Act: 4.3945. Min Act: -0.1700

Data Index: 4883247 (Open Web Text)

Max Activating Token Index: 1015