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

Dataset: Open Web Text

Neuron 2056 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: 6.6628. Min Range: -6.6628

Max Act: 6.6628. Min Act: -0.1700

Data Index: 4811907 (Open Web Text)

Max Activating Token Index: 957

Text #1

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.4445. Min Act: -0.1700

Data Index: 2115822 (Open Web Text)

Max Activating Token Index: 783

Text #2

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.5115. Min Act: -0.1700

Data Index: 4951838 (Open Web Text)

Max Activating Token Index: 955

Text #3

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.5379. Min Act: -0.1700

Data Index: 7409617 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.4898. Min Act: -0.1700

Data Index: 2948151 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.4680. Min Act: -0.1700

Data Index: 2473964 (Open Web Text)

Max Activating Token Index: 712

Text #6

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.4253. Min Act: -0.1700

Data Index: 6991013 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.4025. Min Act: -0.1700

Data Index: 6077884 (Open Web Text)

Max Activating Token Index: 211

Text #8

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.3091. Min Act: -0.1700

Data Index: 8807560 (Open Web Text)

Max Activating Token Index: 821

Text #9

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2802. Min Act: -0.1700

Data Index: 2332372 (Open Web Text)

Max Activating Token Index: 500

Text #10

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2956. Min Act: -0.1700

Data Index: 6976929 (Open Web Text)

Max Activating Token Index: 722

Text #11

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2820. Min Act: -0.1700

Data Index: 2666976 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2338. Min Act: -0.1700

Data Index: 5894909 (Open Web Text)

Max Activating Token Index: 90

Text #13

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2140. Min Act: -0.1700

Data Index: 8125885 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2490. Min Act: -0.1700

Data Index: 3798371 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2710. Min Act: -0.1700

Data Index: 683080 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.1989. Min Act: -0.1700

Data Index: 6560656 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2232. Min Act: -0.1700

Data Index: 6532807 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.2164. Min Act: -0.1700

Data Index: 7140774 (Open Web Text)

Max Activating Token Index: 920

Text #19

Max Range: 6.6628. Min Range: -6.6628

Max Act: 6.1735. Min Act: -0.1700

Data Index: 2055192 (Open Web Text)

Max Activating Token Index: 407