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

Dataset: Open Web Text

Neuron 1178 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: 3.5102. Min Range: -3.5102

Max Act: 3.5102. Min Act: -0.1700

Data Index: 3213964 (Open Web Text)

Max Activating Token Index: 481

Text #1

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.4515. Min Act: -0.1700

Data Index: 6278005 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.4460. Min Act: -0.1700

Data Index: 4664272 (Open Web Text)

Max Activating Token Index: 589

Text #3

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3978. Min Act: -0.1700

Data Index: 5158412 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.4065. Min Act: -0.1700

Data Index: 8123105 (Open Web Text)

Max Activating Token Index: 945

Text #5

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3932. Min Act: -0.1700

Data Index: 7075937 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3655. Min Act: -0.1700

Data Index: 7954928 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3874. Min Act: -0.1700

Data Index: 3390907 (Open Web Text)

Max Activating Token Index: 124

Text #8

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3603. Min Act: -0.1700

Data Index: 7407402 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3625. Min Act: -0.1700

Data Index: 7075932 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3282. Min Act: -0.1700

Data Index: 3543620 (Open Web Text)

Max Activating Token Index: 76

Text #11

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3295. Min Act: -0.1700

Data Index: 5379671 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3347. Min Act: -0.1700

Data Index: 3543615 (Open Web Text)

Max Activating Token Index: 53

Text #13

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3618. Min Act: -0.1700

Data Index: 2585466 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.2843. Min Act: -0.1700

Data Index: 2206974 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3297. Min Act: -0.1700

Data Index: 8493517 (Open Web Text)

Max Activating Token Index: 325

Text #16

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.3157. Min Act: -0.1700

Data Index: 3014926 (Open Web Text)

Max Activating Token Index: 610

Text #17

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.2784. Min Act: -0.1700

Data Index: 2464228 (Open Web Text)

Max Activating Token Index: 698

Text #18

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.2921. Min Act: -0.1700

Data Index: 4908380 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 3.5102. Min Range: -3.5102

Max Act: 3.2745. Min Act: -0.1700

Data Index: 4146433 (Open Web Text)

Max Activating Token Index: 71