Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4933 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0990. Min Range: -6.0990
Max Act: 6.0677. Min Act: -0.1700
Data Index: 3790499 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0990. Min Range: -6.0990
Max Act: 6.0990. Min Act: -0.1700
Data Index: 3524239 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0990. Min Range: -6.0990
Max Act: 6.0052. Min Act: -0.1700
Data Index: 5620373 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0990. Min Range: -6.0990
Max Act: 6.0365. Min Act: -0.1700
Data Index: 3220740 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9740. Min Act: -0.1700
Data Index: 4125624 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9427. Min Act: -0.1700
Data Index: 1998030 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9427. Min Act: -0.1700
Data Index: 8308868 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9115. Min Act: -0.1700
Data Index: 4256660 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9115. Min Act: -0.1700
Data Index: 2738495 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9115. Min Act: -0.1700
Data Index: 8507920 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9115. Min Act: -0.1700
Data Index: 5009838 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.9115. Min Act: -0.1700
Data Index: 7613918 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8802. Min Act: -0.1700
Data Index: 4548973 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8490. Min Act: -0.1700
Data Index: 7417661 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8177. Min Act: -0.1700
Data Index: 4754526 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8177. Min Act: -0.1700
Data Index: 5210091 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8177. Min Act: -0.1700
Data Index: 394123 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8177. Min Act: -0.1700
Data Index: 4468273 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8177. Min Act: -0.1700
Data Index: 7059927 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0990. Min Range: -6.0990
Max Act: 5.8177. Min Act: -0.1700
Data Index: 8746117 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19