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

Dataset: Open Web Text

Neuron 3023 in Layer 0

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: 3.4921. Min Range: -3.4921

Max Act: 3.4921. Min Act: -0.1700

Data Index: 1660467 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.4512. Min Act: -0.1700

Data Index: 6858846 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.4230. Min Act: -0.1700

Data Index: 1106665 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3624. Min Act: -0.1700

Data Index: 6393174 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3712. Min Act: -0.1700

Data Index: 913556 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3679. Min Act: -0.1700

Data Index: 8296222 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3597. Min Act: -0.1700

Data Index: 4393607 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3448. Min Act: -0.1700

Data Index: 8546657 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3464. Min Act: -0.1700

Data Index: 973902 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3266. Min Act: -0.1700

Data Index: 7208207 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3281. Min Act: -0.1700

Data Index: 5821788 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3318. Min Act: -0.1700

Data Index: 7576262 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3150. Min Act: -0.1700

Data Index: 2794733 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3119. Min Act: -0.1700

Data Index: 6487524 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3092. Min Act: -0.1700

Data Index: 4283685 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.2989. Min Act: -0.1700

Data Index: 6484502 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.2932. Min Act: -0.1700

Data Index: 8089883 (Open Web Text)

Max Activating Token Index: 27

Text #17

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3069. Min Act: -0.1700

Data Index: 900303 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3040. Min Act: -0.1700

Data Index: 6335549 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3022. Min Act: -0.1700

Data Index: 6413945 (Open Web Text)

Max Activating Token Index: 9