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

Dataset: Open Web Text

Neuron 2715 in Layer 3

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: 4.8939. Min Range: -4.8939

Max Act: 4.8939. Min Act: -0.1700

Data Index: 1118574 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.7034. Min Act: -0.1700

Data Index: 166337 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.6513. Min Act: -0.1700

Data Index: 7383075 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.6557. Min Act: -0.1700

Data Index: 4445554 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.6209. Min Act: -0.1700

Data Index: 8312358 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.6318. Min Act: -0.1700

Data Index: 1343478 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.6067. Min Act: -0.1700

Data Index: 8459831 (Open Web Text)

Max Activating Token Index: 248

Text #7

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5855. Min Act: -0.1700

Data Index: 5863567 (Open Web Text)

Max Activating Token Index: 281

Text #8

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5485. Min Act: -0.1700

Data Index: 1061913 (Open Web Text)

Max Activating Token Index: 946

Text #9

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5637. Min Act: -0.1700

Data Index: 2158777 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5605. Min Act: -0.1700

Data Index: 1131147 (Open Web Text)

Max Activating Token Index: 208

Text #11

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5750. Min Act: -0.1700

Data Index: 2271233 (Open Web Text)

Max Activating Token Index: 809

Text #12

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5480. Min Act: -0.1700

Data Index: 3647727 (Open Web Text)

Max Activating Token Index: 929

Text #13

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5466. Min Act: -0.1700

Data Index: 3392488 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5527. Min Act: -0.1700

Data Index: 3891982 (Open Web Text)

Max Activating Token Index: 253

Text #15

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5187. Min Act: -0.1700

Data Index: 2564067 (Open Web Text)

Max Activating Token Index: 101

Text #16

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5100. Min Act: -0.1700

Data Index: 474625 (Open Web Text)

Max Activating Token Index: 841

Text #17

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5209. Min Act: -0.1700

Data Index: 7043757 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5462. Min Act: -0.1700

Data Index: 4288427 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 4.8939. Min Range: -4.8939

Max Act: 4.5186. Min Act: -0.1700

Data Index: 8714231 (Open Web Text)

Max Activating Token Index: 905