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

Dataset: Open Web Text

Neuron 867 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: 3.9470. Min Range: -3.9470

Max Act: 3.9470. Min Act: -0.1700

Data Index: 1633068 (Open Web Text)

Max Activating Token Index: 990

Text #1

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.9283. Min Act: -0.1700

Data Index: 3775874 (Open Web Text)

Max Activating Token Index: 59

Text #2

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7971. Min Act: -0.1700

Data Index: 3739625 (Open Web Text)

Max Activating Token Index: 964

Text #3

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.8335. Min Act: -0.1700

Data Index: 8356604 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7847. Min Act: -0.1700

Data Index: 3105405 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7973. Min Act: -0.1700

Data Index: 5142932 (Open Web Text)

Max Activating Token Index: 627

Text #6

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7934. Min Act: -0.1700

Data Index: 5347090 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7945. Min Act: -0.1700

Data Index: 5511433 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7813. Min Act: -0.1700

Data Index: 6309351 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7601. Min Act: -0.1700

Data Index: 312110 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7599. Min Act: -0.1700

Data Index: 6518999 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7605. Min Act: -0.1700

Data Index: 3004820 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7732. Min Act: -0.1700

Data Index: 2806074 (Open Web Text)

Max Activating Token Index: 420

Text #13

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7636. Min Act: -0.1700

Data Index: 7174473 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7524. Min Act: -0.1700

Data Index: 6910214 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7498. Min Act: -0.1700

Data Index: 1259023 (Open Web Text)

Max Activating Token Index: 852

Text #16

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7289. Min Act: -0.1700

Data Index: 2806076 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7333. Min Act: -0.1700

Data Index: 6374859 (Open Web Text)

Max Activating Token Index: 869

Text #18

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7301. Min Act: -0.1700

Data Index: 4302117 (Open Web Text)

Max Activating Token Index: 573

Text #19

Max Range: 3.9470. Min Range: -3.9470

Max Act: 3.7219. Min Act: -0.1700

Data Index: 3390524 (Open Web Text)

Max Activating Token Index: 139