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

Dataset: Open Web Text

Neuron 2298 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: 3.3136. Min Range: -3.3136

Max Act: 3.3136. Min Act: -0.1700

Data Index: 5242423 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2877. Min Act: -0.1700

Data Index: 6315132 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2976. Min Act: -0.1700

Data Index: 4906557 (Open Web Text)

Max Activating Token Index: 246

Text #3

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2511. Min Act: -0.1700

Data Index: 4441464 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2657. Min Act: -0.1700

Data Index: 1690964 (Open Web Text)

Max Activating Token Index: 217

Text #5

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2351. Min Act: -0.1700

Data Index: 3103089 (Open Web Text)

Max Activating Token Index: 680

Text #6

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2378. Min Act: -0.1700

Data Index: 4337487 (Open Web Text)

Max Activating Token Index: 111

Text #7

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2288. Min Act: -0.1700

Data Index: 4548616 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2192. Min Act: -0.1700

Data Index: 1872891 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2105. Min Act: -0.1700

Data Index: 3832814 (Open Web Text)

Max Activating Token Index: 945

Text #10

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2321. Min Act: -0.1700

Data Index: 2003209 (Open Web Text)

Max Activating Token Index: 57

Text #11

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2208. Min Act: -0.1700

Data Index: 5357913 (Open Web Text)

Max Activating Token Index: 914

Text #12

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2183. Min Act: -0.1700

Data Index: 6762600 (Open Web Text)

Max Activating Token Index: 836

Text #13

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2154. Min Act: -0.1700

Data Index: 7668691 (Open Web Text)

Max Activating Token Index: 737

Text #14

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2076. Min Act: -0.1700

Data Index: 4906556 (Open Web Text)

Max Activating Token Index: 459

Text #15

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.1970. Min Act: -0.1700

Data Index: 2117354 (Open Web Text)

Max Activating Token Index: 933

Text #16

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2078. Min Act: -0.1700

Data Index: 6210908 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.1894. Min Act: -0.1700

Data Index: 1032260 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2048. Min Act: -0.1700

Data Index: 2542032 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 3.3136. Min Range: -3.3136

Max Act: 3.2193. Min Act: -0.1700

Data Index: 7441409 (Open Web Text)

Max Activating Token Index: 12