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

Dataset: Open Web Text

Neuron 1726 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: 3.2797. Min Range: -3.2797

Max Act: 3.2702. Min Act: -0.1700

Data Index: 4778931 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2794. Min Act: -0.1700

Data Index: 2683331 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2797. Min Act: -0.1700

Data Index: 6686079 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2578. Min Act: -0.1700

Data Index: 5739188 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2446. Min Act: -0.1697

Data Index: 5070264 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2262. Min Act: -0.1700

Data Index: 4110406 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2495. Min Act: -0.1700

Data Index: 1565003 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2445. Min Act: -0.1700

Data Index: 8466627 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2384. Min Act: -0.1700

Data Index: 3292613 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2356. Min Act: -0.1700

Data Index: 7795715 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2292. Min Act: -0.1699

Data Index: 3205996 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2541. Min Act: -0.1700

Data Index: 2666203 (Open Web Text)

Max Activating Token Index: 1021

Text #12

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2391. Min Act: -0.1700

Data Index: 2209518 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2569. Min Act: -0.1700

Data Index: 5386780 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2048. Min Act: -0.1700

Data Index: 3825020 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2166. Min Act: -0.1696

Data Index: 1731070 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2001. Min Act: -0.1700

Data Index: 4712777 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.1885. Min Act: -0.1700

Data Index: 214591 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2207. Min Act: -0.1700

Data Index: 2161332 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.1998. Min Act: -0.1700

Data Index: 851966 (Open Web Text)

Max Activating Token Index: 1022