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

Dataset: Open Web Text

Neuron 20 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: 5.3532. Min Range: -5.3532

Max Act: 5.3532. Min Act: -0.1700

Data Index: 6452855 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.3081. Min Act: -0.1700

Data Index: 5061636 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2646. Min Act: -0.1700

Data Index: 2965747 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2492. Min Act: -0.1700

Data Index: 2230424 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2512. Min Act: -0.1700

Data Index: 4986858 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2487. Min Act: -0.1700

Data Index: 6233501 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2283. Min Act: -0.1700

Data Index: 2322235 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2238. Min Act: -0.1700

Data Index: 2762189 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2203. Min Act: -0.1700

Data Index: 2111459 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2206. Min Act: -0.1700

Data Index: 4179283 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2267. Min Act: -0.1700

Data Index: 1256677 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1868. Min Act: -0.1700

Data Index: 4945905 (Open Web Text)

Max Activating Token Index: 1005

Text #12

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1933. Min Act: -0.1700

Data Index: 4865636 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1094544 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1915. Min Act: -0.1700

Data Index: 4835305 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1886. Min Act: -0.1700

Data Index: 4299995 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2137. Min Act: -0.1700

Data Index: 4286078 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1747. Min Act: -0.1700

Data Index: 277353 (Open Web Text)

Max Activating Token Index: 1014

Text #18

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1768. Min Act: -0.1700

Data Index: 3920347 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.2059. Min Act: -0.1700

Data Index: 3514735 (Open Web Text)

Max Activating Token Index: 26