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

Dataset: Open Web Text

Neuron 189 in Layer 0

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: 1.4172. Min Range: -1.4172

Max Act: 1.4172. Min Act: -0.1656

Data Index: 5981286 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3934. Min Act: -0.1656

Data Index: 6754227 (Open Web Text)

Max Activating Token Index: 557

Text #2

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3811. Min Act: -0.1656

Data Index: 5698218 (Open Web Text)

Max Activating Token Index: 786

Text #3

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3507. Min Act: -0.1656

Data Index: 6620838 (Open Web Text)

Max Activating Token Index: 589

Text #4

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3289. Min Act: -0.1656

Data Index: 6269294 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3288. Min Act: -0.1656

Data Index: 8623195 (Open Web Text)

Max Activating Token Index: 461

Text #6

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3176. Min Act: -0.1656

Data Index: 2525488 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3162. Min Act: -0.1656

Data Index: 8715430 (Open Web Text)

Max Activating Token Index: 701

Text #8

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3106. Min Act: -0.1656

Data Index: 3043026 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3048. Min Act: -0.1656

Data Index: 6154265 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3007. Min Act: -0.1656

Data Index: 5981283 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2990. Min Act: -0.1656

Data Index: 1225482 (Open Web Text)

Max Activating Token Index: 722

Text #12

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2887. Min Act: -0.1656

Data Index: 284952 (Open Web Text)

Max Activating Token Index: 396

Text #13

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2855. Min Act: -0.1656

Data Index: 550139 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2862. Min Act: -0.1656

Data Index: 7111547 (Open Web Text)

Max Activating Token Index: 384

Text #15

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2855. Min Act: -0.1656

Data Index: 544843 (Open Web Text)

Max Activating Token Index: 732

Text #16

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2895. Min Act: -0.1656

Data Index: 5726519 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2892. Min Act: -0.1656

Data Index: 2560759 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2850. Min Act: -0.1656

Data Index: 2251743 (Open Web Text)

Max Activating Token Index: 883

Text #19

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.2819. Min Act: -0.1656

Data Index: 3522762 (Open Web Text)

Max Activating Token Index: 681