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

Dataset: Open Web Text

Neuron 941 in Layer 3

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: 3.5620. Min Range: -3.5620

Max Act: 3.5556. Min Act: -0.1700

Data Index: 6339956 (Open Web Text)

Max Activating Token Index: 240

Text #1

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.5588. Min Act: -0.1700

Data Index: 1870974 (Open Web Text)

Max Activating Token Index: 869

Text #2

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.5567. Min Act: -0.1700

Data Index: 7494573 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.5620. Min Act: -0.1700

Data Index: 643765 (Open Web Text)

Max Activating Token Index: 276

Text #4

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.5146. Min Act: -0.1700

Data Index: 5674580 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4940. Min Act: -0.1700

Data Index: 7031595 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.5043. Min Act: -0.1700

Data Index: 6939159 (Open Web Text)

Max Activating Token Index: 743

Text #7

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4636. Min Act: -0.1700

Data Index: 5978463 (Open Web Text)

Max Activating Token Index: 71

Text #8

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4714. Min Act: -0.1700

Data Index: 5358223 (Open Web Text)

Max Activating Token Index: 880

Text #9

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4790. Min Act: -0.1700

Data Index: 5674577 (Open Web Text)

Max Activating Token Index: 431

Text #10

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4812. Min Act: -0.1700

Data Index: 3918525 (Open Web Text)

Max Activating Token Index: 53

Text #11

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4235. Min Act: -0.1700

Data Index: 7484633 (Open Web Text)

Max Activating Token Index: 177

Text #12

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4277. Min Act: -0.1700

Data Index: 4243717 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4336. Min Act: -0.1700

Data Index: 5812006 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4248. Min Act: -0.1700

Data Index: 2088412 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4335. Min Act: -0.1700

Data Index: 1870976 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4281. Min Act: -0.1700

Data Index: 3256332 (Open Web Text)

Max Activating Token Index: 356

Text #17

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4027. Min Act: -0.1700

Data Index: 2215031 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4213. Min Act: -0.1700

Data Index: 5668162 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 3.5620. Min Range: -3.5620

Max Act: 3.4224. Min Act: -0.1700

Data Index: 2347971 (Open Web Text)

Max Activating Token Index: 311