Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1607. Min Range: -8.1607
Max Act: 8.1607. Min Act: -0.1700
Data Index: 2570676 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.9732. Min Act: -0.1700
Data Index: 4625788 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.9732. Min Act: -0.1700
Data Index: 6823231 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.8482. Min Act: -0.1700
Data Index: 8527885 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.8482. Min Act: -0.1700
Data Index: 6903785 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7857. Min Act: -0.1700
Data Index: 3154854 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7232. Min Act: -0.1700
Data Index: 5922612 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7232. Min Act: -0.1700
Data Index: 7096274 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7857. Min Act: -0.1700
Data Index: 2304610 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7232. Min Act: -0.1700
Data Index: 2369823 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7232. Min Act: -0.1700
Data Index: 5889108 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7232. Min Act: -0.1700
Data Index: 1265812 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.6607. Min Act: -0.1700
Data Index: 7930855 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.7232. Min Act: -0.1700
Data Index: 6580133 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.6607. Min Act: -0.1700
Data Index: 6026962 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.6607. Min Act: -0.1700
Data Index: 7281228 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.5982. Min Act: -0.1700
Data Index: 163362 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.6607. Min Act: -0.1700
Data Index: 5080805 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.6607. Min Act: -0.1700
Data Index: 8357324 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1607. Min Range: -8.1607
Max Act: 7.6607. Min Act: -0.1700
Data Index: 5881444 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19