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

Dataset: Open Web Text

Neuron 2123 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: 4.0965. Min Range: -4.0965

Max Act: 4.0965. Min Act: -0.1700

Data Index: 678420 (Open Web Text)

Max Activating Token Index: 306

Text #1

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0748. Min Act: -0.1700

Data Index: 6415590 (Open Web Text)

Max Activating Token Index: 381

Text #2

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0321. Min Act: -0.1700

Data Index: 3400292 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0433. Min Act: -0.1700

Data Index: 4462090 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0085. Min Act: -0.1700

Data Index: 5338663 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0458. Min Act: -0.1700

Data Index: 1807926 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0193. Min Act: -0.1700

Data Index: 1856582 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0301. Min Act: -0.1700

Data Index: 4959347 (Open Web Text)

Max Activating Token Index: 139

Text #8

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0188. Min Act: -0.1700

Data Index: 3018036 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0628. Min Act: -0.1700

Data Index: 7978783 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0015. Min Act: -0.1700

Data Index: 1632490 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.0965. Min Range: -4.0965

Max Act: 3.9953. Min Act: -0.1700

Data Index: 8606134 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 4.0965. Min Range: -4.0965

Max Act: 3.9972. Min Act: -0.1700

Data Index: 8561437 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0110. Min Act: -0.1700

Data Index: 4854731 (Open Web Text)

Max Activating Token Index: 54

Text #14

Max Range: 4.0965. Min Range: -4.0965

Max Act: 3.9639. Min Act: -0.1700

Data Index: 1517425 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 4.0965. Min Range: -4.0965

Max Act: 3.9764. Min Act: -0.1700

Data Index: 3042832 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 4.0965. Min Range: -4.0965

Max Act: 3.9860. Min Act: -0.1700

Data Index: 6076890 (Open Web Text)

Max Activating Token Index: 647

Text #17

Max Range: 4.0965. Min Range: -4.0965

Max Act: 4.0367. Min Act: -0.1700

Data Index: 5870852 (Open Web Text)

Max Activating Token Index: 582

Text #18

Max Range: 4.0965. Min Range: -4.0965

Max Act: 3.9751. Min Act: -0.1700

Data Index: 2461466 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 4.0965. Min Range: -4.0965

Max Act: 3.9677. Min Act: -0.1700

Data Index: 1242069 (Open Web Text)

Max Activating Token Index: 812