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

Dataset: Open Web Text

Neuron 176 in Layer 5

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: 3.5419. Min Range: -3.5419

Max Act: 3.5419. Min Act: -0.1700

Data Index: 6660714 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.5051. Min Act: -0.1700

Data Index: 2323455 (Open Web Text)

Max Activating Token Index: 586

Text #2

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4905. Min Act: -0.1700

Data Index: 5931782 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4591. Min Act: -0.1700

Data Index: 4392020 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4198. Min Act: -0.1700

Data Index: 7935533 (Open Web Text)

Max Activating Token Index: 426

Text #5

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4215. Min Act: -0.1700

Data Index: 3298954 (Open Web Text)

Max Activating Token Index: 846

Text #6

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4056. Min Act: -0.1700

Data Index: 2659581 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3972. Min Act: -0.1700

Data Index: 6765363 (Open Web Text)

Max Activating Token Index: 326

Text #8

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3764. Min Act: -0.1700

Data Index: 5058882 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4016. Min Act: -0.1700

Data Index: 646230 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.4038. Min Act: -0.1700

Data Index: 4252381 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3777. Min Act: -0.1700

Data Index: 4733787 (Open Web Text)

Max Activating Token Index: 901

Text #12

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3831. Min Act: -0.1700

Data Index: 2050322 (Open Web Text)

Max Activating Token Index: 953

Text #13

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3686. Min Act: -0.1700

Data Index: 2039579 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3788. Min Act: -0.1700

Data Index: 8309382 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3671. Min Act: -0.1700

Data Index: 1525392 (Open Web Text)

Max Activating Token Index: 229

Text #16

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3793. Min Act: -0.1700

Data Index: 3509529 (Open Web Text)

Max Activating Token Index: 998

Text #17

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3786. Min Act: -0.1700

Data Index: 3383325 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3843. Min Act: -0.1700

Data Index: 7299220 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3560. Min Act: -0.1700

Data Index: 526852 (Open Web Text)

Max Activating Token Index: 453