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

Dataset: Open Web Text

Neuron 1680 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: 4.4291. Min Range: -4.4291

Max Act: 4.4291. Min Act: -0.1700

Data Index: 3253883 (Open Web Text)

Max Activating Token Index: 467

Text #1

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3634. Min Act: -0.1700

Data Index: 6499795 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3666. Min Act: -0.1700

Data Index: 5030582 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3146. Min Act: -0.1700

Data Index: 7210037 (Open Web Text)

Max Activating Token Index: 109

Text #4

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3172. Min Act: -0.1700

Data Index: 2300824 (Open Web Text)

Max Activating Token Index: 712

Text #5

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2937. Min Act: -0.1700

Data Index: 2740053 (Open Web Text)

Max Activating Token Index: 94

Text #6

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2970. Min Act: -0.1700

Data Index: 6143220 (Open Web Text)

Max Activating Token Index: 114

Text #7

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2953. Min Act: -0.1700

Data Index: 6219112 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3091. Min Act: -0.1700

Data Index: 700614 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2717. Min Act: -0.1700

Data Index: 8168520 (Open Web Text)

Max Activating Token Index: 85

Text #10

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2652. Min Act: -0.1700

Data Index: 2483123 (Open Web Text)

Max Activating Token Index: 314

Text #11

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3052. Min Act: -0.1700

Data Index: 5946521 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3288. Min Act: -0.1700

Data Index: 5902658 (Open Web Text)

Max Activating Token Index: 993

Text #13

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2587. Min Act: -0.1700

Data Index: 3873906 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2724. Min Act: -0.1700

Data Index: 4683917 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2463. Min Act: -0.1700

Data Index: 1438029 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2948. Min Act: -0.1700

Data Index: 2527617 (Open Web Text)

Max Activating Token Index: 985

Text #17

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.1983. Min Act: -0.1700

Data Index: 6774741 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2819. Min Act: -0.1700

Data Index: 5509756 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2532. Min Act: -0.1700

Data Index: 3602639 (Open Web Text)

Max Activating Token Index: 308