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

Dataset: Open Web Text

Neuron 191 in Layer 6

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: 3.5034. Min Range: -3.5034

Max Act: 3.5034. Min Act: -0.1700

Data Index: 6773946 (Open Web Text)

Max Activating Token Index: 920

Text #1

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.4644. Min Act: -0.1700

Data Index: 2104224 (Open Web Text)

Max Activating Token Index: 935

Text #2

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.4566. Min Act: -0.1700

Data Index: 8427311 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.4358. Min Act: -0.1700

Data Index: 2104223 (Open Web Text)

Max Activating Token Index: 971

Text #4

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3988. Min Act: -0.1700

Data Index: 3699155 (Open Web Text)

Max Activating Token Index: 934

Text #5

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3956. Min Act: -0.1700

Data Index: 6847428 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3281. Min Act: -0.1700

Data Index: 2339764 (Open Web Text)

Max Activating Token Index: 372

Text #7

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3535. Min Act: -0.1700

Data Index: 3854238 (Open Web Text)

Max Activating Token Index: 889

Text #8

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3593. Min Act: -0.1700

Data Index: 569019 (Open Web Text)

Max Activating Token Index: 879

Text #9

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3489. Min Act: -0.1700

Data Index: 864827 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3368. Min Act: -0.1700

Data Index: 47509 (Open Web Text)

Max Activating Token Index: 872

Text #11

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3079. Min Act: -0.1700

Data Index: 4556943 (Open Web Text)

Max Activating Token Index: 516

Text #12

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.3199. Min Act: -0.1700

Data Index: 1689604 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.2892. Min Act: -0.1700

Data Index: 1836720 (Open Web Text)

Max Activating Token Index: 860

Text #14

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.2777. Min Act: -0.1700

Data Index: 7779247 (Open Web Text)

Max Activating Token Index: 721

Text #15

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.2803. Min Act: -0.1700

Data Index: 6860688 (Open Web Text)

Max Activating Token Index: 828

Text #16

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.2723. Min Act: -0.1700

Data Index: 6868387 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.2829. Min Act: -0.1700

Data Index: 6696877 (Open Web Text)

Max Activating Token Index: 866

Text #18

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.2458. Min Act: -0.1700

Data Index: 2821676 (Open Web Text)

Max Activating Token Index: 727

Text #19

Max Range: 3.5034. Min Range: -3.5034

Max Act: 3.2647. Min Act: -0.1700

Data Index: 4727954 (Open Web Text)

Max Activating Token Index: 616