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

Dataset: Open Web Text

Neuron 1950 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: 1.1194. Min Range: -1.1194

Max Act: 1.1194. Min Act: -0.1700

Data Index: 1697897 (Open Web Text)

Max Activating Token Index: 993

Text #1

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.1118. Min Act: -0.1700

Data Index: 7158908 (Open Web Text)

Max Activating Token Index: 986

Text #2

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0876. Min Act: -0.1700

Data Index: 4379099 (Open Web Text)

Max Activating Token Index: 988

Text #3

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0737. Min Act: -0.1700

Data Index: 4169174 (Open Web Text)

Max Activating Token Index: 990

Text #4

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0775. Min Act: -0.1700

Data Index: 3280505 (Open Web Text)

Max Activating Token Index: 994

Text #5

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0574. Min Act: -0.1700

Data Index: 2895125 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0642. Min Act: -0.1700

Data Index: 4637786 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0500. Min Act: -0.1700

Data Index: 425126 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0464. Min Act: -0.1700

Data Index: 4252185 (Open Web Text)

Max Activating Token Index: 999

Text #9

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0494. Min Act: -0.1700

Data Index: 8182541 (Open Web Text)

Max Activating Token Index: 469

Text #10

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0523. Min Act: -0.1700

Data Index: 5621793 (Open Web Text)

Max Activating Token Index: 996

Text #11

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0641. Min Act: -0.1700

Data Index: 3553571 (Open Web Text)

Max Activating Token Index: 987

Text #12

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0313. Min Act: -0.1700

Data Index: 6685254 (Open Web Text)

Max Activating Token Index: 980

Text #13

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0411. Min Act: -0.1700

Data Index: 151396 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0403. Min Act: -0.1700

Data Index: 4249352 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0370. Min Act: -0.1700

Data Index: 2108747 (Open Web Text)

Max Activating Token Index: 995

Text #16

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0389. Min Act: -0.1700

Data Index: 4577938 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0362. Min Act: -0.1700

Data Index: 2418994 (Open Web Text)

Max Activating Token Index: 995

Text #18

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0429. Min Act: -0.1700

Data Index: 3501412 (Open Web Text)

Max Activating Token Index: 991

Text #19

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0285. Min Act: -0.1700

Data Index: 7780881 (Open Web Text)

Max Activating Token Index: 991