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

Dataset: Open Web Text

Neuron 21 in Layer 4

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: 3.4505. Min Range: -3.4505

Max Act: 3.4505. Min Act: -0.1700

Data Index: 1178012 (Open Web Text)

Max Activating Token Index: 134

Text #1

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2790. Min Act: -0.1700

Data Index: 402252 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2595. Min Act: -0.1700

Data Index: 5515365 (Open Web Text)

Max Activating Token Index: 925

Text #3

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2742. Min Act: -0.1700

Data Index: 6918617 (Open Web Text)

Max Activating Token Index: 862

Text #4

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2380. Min Act: -0.1700

Data Index: 8302444 (Open Web Text)

Max Activating Token Index: 1010

Text #5

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2430. Min Act: -0.1700

Data Index: 5909122 (Open Web Text)

Max Activating Token Index: 797

Text #6

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2563. Min Act: -0.1700

Data Index: 1862459 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2307. Min Act: -0.1700

Data Index: 2234630 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2253. Min Act: -0.1700

Data Index: 5343868 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2121. Min Act: -0.1700

Data Index: 6743617 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1945. Min Act: -0.1700

Data Index: 1747398 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1966. Min Act: -0.1700

Data Index: 7601672 (Open Web Text)

Max Activating Token Index: 257

Text #12

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1958. Min Act: -0.1700

Data Index: 3154280 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1829. Min Act: -0.1700

Data Index: 2287061 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1704. Min Act: -0.1700

Data Index: 1547064 (Open Web Text)

Max Activating Token Index: 788

Text #15

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1938. Min Act: -0.1700

Data Index: 4145124 (Open Web Text)

Max Activating Token Index: 433

Text #16

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1998. Min Act: -0.1700

Data Index: 7647382 (Open Web Text)

Max Activating Token Index: 817

Text #17

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1936. Min Act: -0.1700

Data Index: 3153891 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1907. Min Act: -0.1700

Data Index: 1063678 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1675. Min Act: -0.1700

Data Index: 5055755 (Open Web Text)

Max Activating Token Index: 271