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

Dataset: Open Web Text

Neuron 1071 in Layer 1

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: 1.6366. Min Range: -1.6366

Max Act: 1.6366. Min Act: -0.1700

Data Index: 1721127 (Open Web Text)

Max Activating Token Index: 630

Text #1

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.6226. Min Act: -0.1700

Data Index: 5762033 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.6181. Min Act: -0.1700

Data Index: 7859085 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.6070. Min Act: -0.1700

Data Index: 662064 (Open Web Text)

Max Activating Token Index: 732

Text #4

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.6001. Min Act: -0.1700

Data Index: 8490238 (Open Web Text)

Max Activating Token Index: 606

Text #5

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.6020. Min Act: -0.1700

Data Index: 7342002 (Open Web Text)

Max Activating Token Index: 663

Text #6

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.6087. Min Act: -0.1694

Data Index: 66314 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5779. Min Act: -0.1700

Data Index: 4911200 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5762. Min Act: -0.1700

Data Index: 8040354 (Open Web Text)

Max Activating Token Index: 870

Text #9

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5796. Min Act: -0.1700

Data Index: 6565047 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5809. Min Act: -0.1700

Data Index: 7249829 (Open Web Text)

Max Activating Token Index: 109

Text #11

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5727. Min Act: -0.1699

Data Index: 5649902 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5661. Min Act: -0.1700

Data Index: 7936994 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5764. Min Act: -0.1700

Data Index: 2114213 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5657. Min Act: -0.1700

Data Index: 2900437 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5737. Min Act: -0.1700

Data Index: 7429124 (Open Web Text)

Max Activating Token Index: 713

Text #16

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5666. Min Act: -0.1699

Data Index: 7666092 (Open Web Text)

Max Activating Token Index: 872

Text #17

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5597. Min Act: -0.1700

Data Index: 5919819 (Open Web Text)

Max Activating Token Index: 653

Text #18

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5675. Min Act: -0.1700

Data Index: 930180 (Open Web Text)

Max Activating Token Index: 645

Text #19

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5650. Min Act: -0.1700

Data Index: 5770303 (Open Web Text)

Max Activating Token Index: 989