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

Dataset: Open Web Text

Neuron 487 in Layer 2

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: 3.5494. Min Range: -3.5494

Max Act: 3.5494. Min Act: -0.1700

Data Index: 4122117 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.5096. Min Act: -0.1700

Data Index: 314039 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4858. Min Act: -0.1700

Data Index: 320386 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4857. Min Act: -0.1700

Data Index: 7005159 (Open Web Text)

Max Activating Token Index: 980

Text #4

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4632. Min Act: -0.1700

Data Index: 7227669 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4749. Min Act: -0.1700

Data Index: 5578824 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4900. Min Act: -0.1700

Data Index: 2492665 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4430. Min Act: -0.1700

Data Index: 8100979 (Open Web Text)

Max Activating Token Index: 1007

Text #8

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4468. Min Act: -0.1700

Data Index: 5540139 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4319. Min Act: -0.1700

Data Index: 2926844 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4266. Min Act: -0.1700

Data Index: 5219785 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3983. Min Act: -0.1700

Data Index: 7055902 (Open Web Text)

Max Activating Token Index: 810

Text #12

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3853. Min Act: -0.1700

Data Index: 6794231 (Open Web Text)

Max Activating Token Index: 240

Text #13

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3992. Min Act: -0.1700

Data Index: 3992795 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3902. Min Act: -0.1700

Data Index: 4885853 (Open Web Text)

Max Activating Token Index: 937

Text #15

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3882. Min Act: -0.1700

Data Index: 1669027 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3883. Min Act: -0.1700

Data Index: 8721476 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4003. Min Act: -0.1700

Data Index: 5827079 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3932. Min Act: -0.1700

Data Index: 5579068 (Open Web Text)

Max Activating Token Index: 721

Text #19

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3917. Min Act: -0.1700

Data Index: 6013131 (Open Web Text)

Max Activating Token Index: 3