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

Dataset: Open Web Text

Neuron 1864 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: 3.0132. Min Range: -3.0132

Max Act: 3.0132. Min Act: -0.1700

Data Index: 6286942 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.7736. Min Act: -0.1700

Data Index: 6344751 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.8053. Min Act: -0.1700

Data Index: 8019933 (Open Web Text)

Max Activating Token Index: 526

Text #3

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.7189. Min Act: -0.1700

Data Index: 3685056 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.7345. Min Act: -0.1700

Data Index: 2479524 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.6618. Min Act: -0.1700

Data Index: 5332290 (Open Web Text)

Max Activating Token Index: 457

Text #6

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.6279. Min Act: -0.1700

Data Index: 7666369 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5539. Min Act: -0.1700

Data Index: 5670499 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.6182. Min Act: -0.1700

Data Index: 5234393 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5749. Min Act: -0.1700

Data Index: 7941857 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5739. Min Act: -0.1700

Data Index: 3576117 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5399. Min Act: -0.1700

Data Index: 1534388 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5603. Min Act: -0.1700

Data Index: 5197647 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5164. Min Act: -0.1700

Data Index: 5004853 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5324. Min Act: -0.1700

Data Index: 7145069 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5439. Min Act: -0.1700

Data Index: 4268172 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5194. Min Act: -0.1700

Data Index: 5862920 (Open Web Text)

Max Activating Token Index: 817

Text #17

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5063. Min Act: -0.1700

Data Index: 7564500 (Open Web Text)

Max Activating Token Index: 701

Text #18

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5178. Min Act: -0.1700

Data Index: 8236817 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 3.0132. Min Range: -3.0132

Max Act: 2.5162. Min Act: -0.1700

Data Index: 3375455 (Open Web Text)

Max Activating Token Index: 550