Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.9110. Min Act: -0.1700
Data Index: 4314993 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.8173. Min Act: -0.1700
Data Index: 2811635 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.7235. Min Act: -0.1700
Data Index: 165151 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.6610. Min Act: -0.1700
Data Index: 7164889 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.6610. Min Act: -0.1700
Data Index: 7976391 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.6298. Min Act: -0.1700
Data Index: 6099606 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.5360. Min Act: -0.1700
Data Index: 7548557 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.5360. Min Act: -0.1700
Data Index: 4361692 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4735. Min Act: -0.1700
Data Index: 3253055 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4735. Min Act: -0.1700
Data Index: 759547 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4735. Min Act: -0.1700
Data Index: 5248520 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4423. Min Act: -0.1700
Data Index: 6108625 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4735. Min Act: -0.1700
Data Index: 4381452 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4423. Min Act: -0.1700
Data Index: 8735213 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4423. Min Act: -0.1700
Data Index: 2972062 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4423. Min Act: -0.1700
Data Index: 1684518 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4110. Min Act: -0.1700
Data Index: 2252448 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.4110. Min Act: -0.1700
Data Index: 6626487 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.3798. Min Act: -0.1700
Data Index: 2110376 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9110. Min Range: -6.9110
Max Act: 6.3485. Min Act: -0.1700
Data Index: 1838633 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19