Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.8499. Min Act: -0.1700
Data Index: 1864108 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.5999. Min Act: -0.1700
Data Index: 5212502 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.5686. Min Act: -0.1700
Data Index: 3008564 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.5061. Min Act: -0.1700
Data Index: 7383786 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4436. Min Act: -0.1700
Data Index: 7119814 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 3854455 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4124. Min Act: -0.1700
Data Index: 1263251 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 5892421 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 1534200 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 6810039 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 5061384 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4124. Min Act: -0.1700
Data Index: 467960 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 4646374 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 1100147 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3499. Min Act: -0.1700
Data Index: 5761077 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3499. Min Act: -0.1700
Data Index: 8417667 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3499. Min Act: -0.1700
Data Index: 5886080 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3186. Min Act: -0.1700
Data Index: 6624474 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3186. Min Act: -0.1700
Data Index: 2941750 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3186. Min Act: -0.1700
Data Index: 3913187 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19