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

Dataset: Open Web Text

Neuron 1089 in Layer 5

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: 4.3484. Min Range: -4.3484

Max Act: 4.3484. Min Act: -0.1700

Data Index: 2905693 (Open Web Text)

Max Activating Token Index: 121

Text #1

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.3265. Min Act: -0.1700

Data Index: 3025538 (Open Web Text)

Max Activating Token Index: 926

Text #2

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.3020. Min Act: -0.1700

Data Index: 6833611 (Open Web Text)

Max Activating Token Index: 1018

Text #3

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.3031. Min Act: -0.1700

Data Index: 7535270 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2874. Min Act: -0.1700

Data Index: 2190258 (Open Web Text)

Max Activating Token Index: 806

Text #5

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2856. Min Act: -0.1700

Data Index: 3092025 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.3114. Min Act: -0.1700

Data Index: 4958758 (Open Web Text)

Max Activating Token Index: 920

Text #7

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2819. Min Act: -0.1700

Data Index: 1328445 (Open Web Text)

Max Activating Token Index: 916

Text #8

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2343. Min Act: -0.1700

Data Index: 4194493 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2216. Min Act: -0.1700

Data Index: 4525737 (Open Web Text)

Max Activating Token Index: 504

Text #10

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2465. Min Act: -0.1700

Data Index: 7224230 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2178. Min Act: -0.1700

Data Index: 7097153 (Open Web Text)

Max Activating Token Index: 725

Text #12

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2003. Min Act: -0.1700

Data Index: 6421269 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2128. Min Act: -0.1700

Data Index: 8462827 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.1998. Min Act: -0.1700

Data Index: 2485194 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2138. Min Act: -0.1700

Data Index: 4124101 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.2114. Min Act: -0.1700

Data Index: 594015 (Open Web Text)

Max Activating Token Index: 858

Text #17

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.1963. Min Act: -0.1700

Data Index: 6455288 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.1892. Min Act: -0.1700

Data Index: 3786405 (Open Web Text)

Max Activating Token Index: 567

Text #19

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.1707. Min Act: -0.1700

Data Index: 6365439 (Open Web Text)

Max Activating Token Index: 916