Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1918. Min Range: -5.1918
Max Act: 5.1918. Min Act: -0.1700
Data Index: 4792648 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1918. Min Range: -5.1918
Max Act: 5.0668. Min Act: -0.1700
Data Index: 963672 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1918. Min Range: -5.1918
Max Act: 5.0043. Min Act: -0.1700
Data Index: 8378199 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.9731. Min Act: -0.1700
Data Index: 2264582 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.9731. Min Act: -0.1700
Data Index: 7649248 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.9731. Min Act: -0.1700
Data Index: 2581363 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.9106. Min Act: -0.1700
Data Index: 5500344 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.9106. Min Act: -0.1700
Data Index: 4535123 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 4526563 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 6727584 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 38982 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 500486 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.9106. Min Act: -0.1700
Data Index: 2581364 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 451832 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 6512290 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 6051119 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8793. Min Act: -0.1700
Data Index: 744913 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8481. Min Act: -0.1700
Data Index: 4430691 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8481. Min Act: -0.1700
Data Index: 6327243 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1918. Min Range: -5.1918
Max Act: 4.8481. Min Act: -0.1700
Data Index: 85158 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19