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

Dataset: Open Web Text

Neuron 560 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: 4.4938. Min Range: -4.4938

Max Act: 4.4938. Min Act: -0.1700

Data Index: 993182 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.4813. Min Act: -0.1700

Data Index: 4794753 (Open Web Text)

Max Activating Token Index: 108

Text #2

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.4468. Min Act: -0.1700

Data Index: 6193902 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.4686. Min Act: -0.1700

Data Index: 2881988 (Open Web Text)

Max Activating Token Index: 338

Text #4

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.4253. Min Act: -0.1700

Data Index: 396440 (Open Web Text)

Max Activating Token Index: 548

Text #5

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3843. Min Act: -0.1700

Data Index: 1196184 (Open Web Text)

Max Activating Token Index: 448

Text #6

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3593. Min Act: -0.1700

Data Index: 2746333 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3730. Min Act: -0.1700

Data Index: 2513159 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3767. Min Act: -0.1700

Data Index: 5562290 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3650. Min Act: -0.1700

Data Index: 5284709 (Open Web Text)

Max Activating Token Index: 427

Text #10

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3921. Min Act: -0.1700

Data Index: 8381088 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3406. Min Act: -0.1700

Data Index: 6500700 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3337. Min Act: -0.1700

Data Index: 6485087 (Open Web Text)

Max Activating Token Index: 612

Text #13

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3406. Min Act: -0.1700

Data Index: 6010492 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3455. Min Act: -0.1700

Data Index: 3103081 (Open Web Text)

Max Activating Token Index: 716

Text #15

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3585. Min Act: -0.1700

Data Index: 8316305 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3141. Min Act: -0.1700

Data Index: 3792112 (Open Web Text)

Max Activating Token Index: 380

Text #17

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3159. Min Act: -0.1700

Data Index: 6443911 (Open Web Text)

Max Activating Token Index: 673

Text #18

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3453. Min Act: -0.1700

Data Index: 3621280 (Open Web Text)

Max Activating Token Index: 986

Text #19

Max Range: 4.4938. Min Range: -4.4938

Max Act: 4.3265. Min Act: -0.1700

Data Index: 1091684 (Open Web Text)

Max Activating Token Index: 10