Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5600 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2750. Min Range: -8.2750
Max Act: 8.2750. Min Act: -0.1700
Data Index: 6539693 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2750. Min Range: -8.2750
Max Act: 8.2125. Min Act: -0.1700
Data Index: 1937193 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2750. Min Range: -8.2750
Max Act: 8.1500. Min Act: -0.1700
Data Index: 2522942 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2750. Min Range: -8.2750
Max Act: 8.1500. Min Act: -0.1700
Data Index: 5709677 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2750. Min Range: -8.2750
Max Act: 8.0562. Min Act: -0.1700
Data Index: 8732453 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.9625. Min Act: -0.1700
Data Index: 6539698 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.9625. Min Act: -0.1700
Data Index: 2288243 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.9625. Min Act: -0.1700
Data Index: 1162585 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.8687. Min Act: -0.1700
Data Index: 845182 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.8062. Min Act: -0.1700
Data Index: 7195526 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.8062. Min Act: -0.1700
Data Index: 1550519 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.8062. Min Act: -0.1700
Data Index: 4313758 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.7125. Min Act: -0.1700
Data Index: 5692828 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.6812. Min Act: -0.1700
Data Index: 5746153 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.7125. Min Act: -0.1700
Data Index: 264163 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.6812. Min Act: -0.1700
Data Index: 5596321 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.6500. Min Act: -0.1700
Data Index: 1554470 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.6187. Min Act: -0.1700
Data Index: 6289322 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.5875. Min Act: -0.1700
Data Index: 4150533 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2750. Min Range: -8.2750
Max Act: 7.5562. Min Act: -0.1700
Data Index: 2056937 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19