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

Dataset: Open Web Text

Neuron 852 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: 4.3797. Min Range: -4.3797

Max Act: 4.3717. Min Act: -0.1700

Data Index: 3926367 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3797. Min Act: -0.1700

Data Index: 4909789 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3420. Min Act: -0.1700

Data Index: 551373 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3583. Min Act: -0.1700

Data Index: 3169337 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3232. Min Act: -0.1700

Data Index: 5238062 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3337. Min Act: -0.1700

Data Index: 6704415 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3363. Min Act: -0.1700

Data Index: 6816877 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3138. Min Act: -0.1700

Data Index: 7782936 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3346. Min Act: -0.1700

Data Index: 3655248 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3109. Min Act: -0.1700

Data Index: 399106 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3139. Min Act: -0.1700

Data Index: 3299556 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3052. Min Act: -0.1700

Data Index: 3112600 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2968. Min Act: -0.1700

Data Index: 4793145 (Open Web Text)

Max Activating Token Index: 32

Text #13

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3077. Min Act: -0.1700

Data Index: 38096 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2598. Min Act: -0.1700

Data Index: 4187772 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2742. Min Act: -0.1700

Data Index: 1421108 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2671. Min Act: -0.1700

Data Index: 578347 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2808. Min Act: -0.1700

Data Index: 575677 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2671. Min Act: -0.1700

Data Index: 776572 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2585. Min Act: -0.1700

Data Index: 3934955 (Open Web Text)

Max Activating Token Index: 8