Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4872 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.4541. Min Act: -0.1700
Data Index: 1957775 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.4541. Min Act: -0.1700
Data Index: 5751620 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.3916. Min Act: -0.1700
Data Index: 8098581 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.3916. Min Act: -0.1700
Data Index: 1626400 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.2354. Min Act: -0.1700
Data Index: 243 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.2354. Min Act: -0.1700
Data Index: 4896064 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.2354. Min Act: -0.1700
Data Index: 6266055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.2354. Min Act: -0.1700
Data Index: 8094315 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.1729. Min Act: -0.1700
Data Index: 2142602 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.1416. Min Act: -0.1700
Data Index: 8164112 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.1104. Min Act: -0.1700
Data Index: 8480226 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.0479. Min Act: -0.1700
Data Index: 5340992 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4541. Min Range: -5.4541
Max Act: 5.0166. Min Act: -0.1700
Data Index: 1049642 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4541. Min Range: -5.4541
Max Act: 4.9854. Min Act: -0.1700
Data Index: 5445551 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4541. Min Range: -5.4541
Max Act: 4.9854. Min Act: -0.1700
Data Index: 6790891 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4541. Min Range: -5.4541
Max Act: 4.9541. Min Act: -0.1700
Data Index: 8221942 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4541. Min Range: -5.4541
Max Act: 4.9229. Min Act: -0.1700
Data Index: 770646 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4541. Min Range: -5.4541
Max Act: 4.9541. Min Act: -0.1700
Data Index: 15626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4541. Min Range: -5.4541
Max Act: 4.9229. Min Act: -0.1700
Data Index: 3518074 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4541. Min Range: -5.4541
Max Act: 4.9229. Min Act: -0.1700
Data Index: 6328226 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19