Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0091. Min Range: -4.0091
Max Act: 4.0091. Min Act: -0.1700
Data Index: 5436145 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.9466. Min Act: -0.1700
Data Index: 8177328 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.9154. Min Act: -0.1700
Data Index: 2720684 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.9154. Min Act: -0.1700
Data Index: 7067934 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.8841. Min Act: -0.1700
Data Index: 7821216 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.8528. Min Act: -0.1700
Data Index: 2256208 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.8216. Min Act: -0.1700
Data Index: 1787419 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.8216. Min Act: -0.1700
Data Index: 5590832 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7903. Min Act: -0.1700
Data Index: 627604 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7590. Min Act: -0.1700
Data Index: 4550641 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7903. Min Act: -0.1700
Data Index: 8424651 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7590. Min Act: -0.1700
Data Index: 4318872 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7590. Min Act: -0.1700
Data Index: 5177127 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7590. Min Act: -0.1700
Data Index: 1839871 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7277. Min Act: -0.1700
Data Index: 4802371 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7121. Min Act: -0.1700
Data Index: 8278255 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7590. Min Act: -0.1700
Data Index: 8304993 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7277. Min Act: -0.1700
Data Index: 5688406 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7277. Min Act: -0.1700
Data Index: 4264415 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0091. Min Range: -4.0091
Max Act: 3.7121. Min Act: -0.1700
Data Index: 4251682 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19