Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.3907. Min Act: -0.1700
Data Index: 6180223 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.2657. Min Act: -0.1700
Data Index: 4741462 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.2032. Min Act: -0.1700
Data Index: 1622593 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.1407. Min Act: -0.1700
Data Index: 7719805 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.0782. Min Act: -0.1700
Data Index: 8402246 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.0782. Min Act: -0.1700
Data Index: 1606287 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.0782. Min Act: -0.1700
Data Index: 1522745 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.0157. Min Act: -0.1700
Data Index: 3040807 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3907. Min Range: -8.3907
Max Act: 8.0157. Min Act: -0.1700
Data Index: 2401470 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.9532. Min Act: -0.1700
Data Index: 7500046 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.9532. Min Act: -0.1700
Data Index: 180568 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.9219. Min Act: -0.1700
Data Index: 5064436 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.8594. Min Act: -0.1700
Data Index: 120857 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.7032. Min Act: -0.1700
Data Index: 1074784 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.7032. Min Act: -0.1700
Data Index: 5992926 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.6719. Min Act: -0.1700
Data Index: 2834751 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.5469. Min Act: -0.1700
Data Index: 662156 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.5469. Min Act: -0.1700
Data Index: 8055956 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.5469. Min Act: -0.1700
Data Index: 1649392 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3907. Min Range: -8.3907
Max Act: 7.5157. Min Act: -0.1700
Data Index: 1401185 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19