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

Dataset: Open Web Text

Neuron 1141 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: 1.4603. Min Range: -1.4603

Max Act: 1.4603. Min Act: -0.0392

Data Index: 4483240 (Open Web Text)

Max Activating Token Index: 623

Text #1

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4523. Min Act: -0.0392

Data Index: 7147904 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4559. Min Act: -0.0392

Data Index: 6291440 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4560. Min Act: -0.0392

Data Index: 6882774 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4479. Min Act: -0.0392

Data Index: 3829106 (Open Web Text)

Max Activating Token Index: 969

Text #5

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4389. Min Act: -0.0544

Data Index: 5792925 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4410. Min Act: -0.1017

Data Index: 1677985 (Open Web Text)

Max Activating Token Index: 449

Text #7

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4174. Min Act: -0.0392

Data Index: 3190643 (Open Web Text)

Max Activating Token Index: 531

Text #8

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4228. Min Act: -0.0392

Data Index: 2310758 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4176. Min Act: -0.0670

Data Index: 3698082 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4164. Min Act: -0.0392

Data Index: 4504979 (Open Web Text)

Max Activating Token Index: 88

Text #11

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4077. Min Act: -0.0672

Data Index: 123195 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4116. Min Act: -0.0522

Data Index: 3886848 (Open Web Text)

Max Activating Token Index: 999

Text #13

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3980. Min Act: -0.0632

Data Index: 3698087 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3992. Min Act: -0.0392

Data Index: 3238778 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4048. Min Act: -0.0565

Data Index: 2641913 (Open Web Text)

Max Activating Token Index: 377

Text #16

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3998. Min Act: -0.0392

Data Index: 2310754 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4019. Min Act: -0.0740

Data Index: 4106199 (Open Web Text)

Max Activating Token Index: 834

Text #18

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4042. Min Act: -0.0392

Data Index: 2310722 (Open Web Text)

Max Activating Token Index: 742

Text #19

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3964. Min Act: -0.0912

Data Index: 3596696 (Open Web Text)

Max Activating Token Index: 667