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

Dataset: Open Web Text

Neuron 672 in Layer 2

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: 1.7206. Min Range: -1.7206

Max Act: 1.7205. Min Act: -0.1700

Data Index: 3728765 (Open Web Text)

Max Activating Token Index: 236

Text #1

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.7154. Min Act: -0.1700

Data Index: 2930972 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.7206. Min Act: -0.1700

Data Index: 8237693 (Open Web Text)

Max Activating Token Index: 1017

Text #3

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6906. Min Act: -0.1700

Data Index: 1210688 (Open Web Text)

Max Activating Token Index: 921

Text #4

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6939. Min Act: -0.1700

Data Index: 3901296 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.7017. Min Act: -0.1700

Data Index: 1786772 (Open Web Text)

Max Activating Token Index: 563

Text #6

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6636. Min Act: -0.1700

Data Index: 6055011 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6753. Min Act: -0.1700

Data Index: 1683568 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6697. Min Act: -0.1700

Data Index: 4870375 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6633. Min Act: -0.1700

Data Index: 556420 (Open Web Text)

Max Activating Token Index: 977

Text #10

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6404. Min Act: -0.1700

Data Index: 3041467 (Open Web Text)

Max Activating Token Index: 250

Text #11

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6609. Min Act: -0.1700

Data Index: 5691284 (Open Web Text)

Max Activating Token Index: 842

Text #12

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6481. Min Act: -0.1700

Data Index: 5554348 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6307. Min Act: -0.1700

Data Index: 2211476 (Open Web Text)

Max Activating Token Index: 369

Text #14

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6293. Min Act: -0.1700

Data Index: 3077997 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6310. Min Act: -0.1700

Data Index: 7897162 (Open Web Text)

Max Activating Token Index: 850

Text #16

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6320. Min Act: -0.1700

Data Index: 4602488 (Open Web Text)

Max Activating Token Index: 304

Text #17

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6303. Min Act: -0.1700

Data Index: 3437347 (Open Web Text)

Max Activating Token Index: 1011

Text #18

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6204. Min Act: -0.1700

Data Index: 4993597 (Open Web Text)

Max Activating Token Index: 230

Text #19

Max Range: 1.7206. Min Range: -1.7206

Max Act: 1.6228. Min Act: -0.1700

Data Index: 4591331 (Open Web Text)

Max Activating Token Index: 144