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

Dataset: Open Web Text

Neuron 603 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: 4.5532. Min Range: -4.5532

Max Act: 4.5532. Min Act: -0.1700

Data Index: 3370008 (Open Web Text)

Max Activating Token Index: 369

Text #1

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.5083. Min Act: -0.1700

Data Index: 2211262 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.4269. Min Act: -0.1700

Data Index: 960169 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.4330. Min Act: -0.1700

Data Index: 7461710 (Open Web Text)

Max Activating Token Index: 99

Text #4

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.4536. Min Act: -0.1700

Data Index: 2921081 (Open Web Text)

Max Activating Token Index: 735

Text #5

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.4557. Min Act: -0.1700

Data Index: 986308 (Open Web Text)

Max Activating Token Index: 449

Text #6

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.4194. Min Act: -0.1700

Data Index: 2354016 (Open Web Text)

Max Activating Token Index: 93

Text #7

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.4033. Min Act: -0.1700

Data Index: 4753708 (Open Web Text)

Max Activating Token Index: 698

Text #8

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.4114. Min Act: -0.1700

Data Index: 7782439 (Open Web Text)

Max Activating Token Index: 257

Text #9

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3916. Min Act: -0.1700

Data Index: 3582189 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3585. Min Act: -0.1700

Data Index: 1706108 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3831. Min Act: -0.1700

Data Index: 4329348 (Open Web Text)

Max Activating Token Index: 802

Text #12

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3532. Min Act: -0.1700

Data Index: 7878571 (Open Web Text)

Max Activating Token Index: 505

Text #13

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3785. Min Act: -0.1700

Data Index: 2857575 (Open Web Text)

Max Activating Token Index: 984

Text #14

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3793. Min Act: -0.1700

Data Index: 3637614 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3245. Min Act: -0.1700

Data Index: 4872633 (Open Web Text)

Max Activating Token Index: 430

Text #16

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3388. Min Act: -0.1700

Data Index: 666832 (Open Web Text)

Max Activating Token Index: 44

Text #17

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3284. Min Act: -0.1700

Data Index: 5518689 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3316. Min Act: -0.1700

Data Index: 6570202 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 4.5532. Min Range: -4.5532

Max Act: 4.3480. Min Act: -0.1700

Data Index: 6641117 (Open Web Text)

Max Activating Token Index: 477