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

Dataset: Open Web Text

Neuron 2805 in Layer 5

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: 4.2027. Min Range: -4.2027

Max Act: 4.2027. Min Act: -0.1700

Data Index: 8761882 (Open Web Text)

Max Activating Token Index: 961

Text #1

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9882. Min Act: -0.1700

Data Index: 885038 (Open Web Text)

Max Activating Token Index: 85

Text #2

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9604. Min Act: -0.1700

Data Index: 2064705 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9970. Min Act: -0.1700

Data Index: 217968 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.9378. Min Act: -0.1700

Data Index: 982102 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.8467. Min Act: -0.1700

Data Index: 1478317 (Open Web Text)

Max Activating Token Index: 592

Text #6

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7683. Min Act: -0.1700

Data Index: 4130044 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7893. Min Act: -0.1700

Data Index: 2961590 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.8025. Min Act: -0.1700

Data Index: 7545577 (Open Web Text)

Max Activating Token Index: 416

Text #9

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7615. Min Act: -0.1700

Data Index: 7405168 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7255. Min Act: -0.1700

Data Index: 7742754 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7034. Min Act: -0.1700

Data Index: 3698371 (Open Web Text)

Max Activating Token Index: 236

Text #12

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7034. Min Act: -0.1700

Data Index: 7797498 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7042. Min Act: -0.1700

Data Index: 3225770 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.6988. Min Act: -0.1700

Data Index: 2928496 (Open Web Text)

Max Activating Token Index: 168

Text #15

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.7205. Min Act: -0.1700

Data Index: 8521185 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.6825. Min Act: -0.1700

Data Index: 3632017 (Open Web Text)

Max Activating Token Index: 247

Text #17

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.6756. Min Act: -0.1700

Data Index: 4598524 (Open Web Text)

Max Activating Token Index: 475

Text #18

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.6846. Min Act: -0.1700

Data Index: 7730169 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 4.2027. Min Range: -4.2027

Max Act: 3.6943. Min Act: -0.1700

Data Index: 1565767 (Open Web Text)

Max Activating Token Index: 442