Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1840. Min Range: -6.1840
Max Act: 6.1840. Min Act: -0.1700
Data Index: 6751597 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1840. Min Range: -6.1840
Max Act: 6.1215. Min Act: -0.1700
Data Index: 126911 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1840. Min Range: -6.1840
Max Act: 6.1215. Min Act: -0.1700
Data Index: 1841694 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1840. Min Range: -6.1840
Max Act: 6.0590. Min Act: -0.1700
Data Index: 4967019 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1840. Min Range: -6.1840
Max Act: 6.0590. Min Act: -0.1700
Data Index: 2404912 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1840. Min Range: -6.1840
Max Act: 6.0590. Min Act: -0.1700
Data Index: 2335339 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1840. Min Range: -6.1840
Max Act: 6.0590. Min Act: -0.1700
Data Index: 8256941 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9965. Min Act: -0.1700
Data Index: 5919667 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9965. Min Act: -0.1700
Data Index: 5903606 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9965. Min Act: -0.1700
Data Index: 8265124 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9965. Min Act: -0.1700
Data Index: 7002648 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9965. Min Act: -0.1700
Data Index: 3339467 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9653. Min Act: -0.1700
Data Index: 2014301 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9340. Min Act: -0.1700
Data Index: 3557039 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9340. Min Act: -0.1700
Data Index: 3013575 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9340. Min Act: -0.1700
Data Index: 7060477 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.9340. Min Act: -0.1700
Data Index: 4609420 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.8715. Min Act: -0.1700
Data Index: 151786 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.8715. Min Act: -0.1700
Data Index: 5035171 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1840. Min Range: -6.1840
Max Act: 5.8403. Min Act: -0.1700
Data Index: 5970583 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19