Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4615 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2719. Min Range: -7.2719
Max Act: 7.2719. Min Act: -0.1700
Data Index: 5722639 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2719. Min Range: -7.2719
Max Act: 7.0219. Min Act: -0.1700
Data Index: 5475858 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.9907. Min Act: -0.1700
Data Index: 672557 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.9907. Min Act: -0.1700
Data Index: 2101811 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.9282. Min Act: -0.1700
Data Index: 2638809 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.9282. Min Act: -0.1700
Data Index: 6555051 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.8969. Min Act: -0.1700
Data Index: 8795884 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.8657. Min Act: -0.1700
Data Index: 7432766 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.8657. Min Act: -0.1700
Data Index: 4264674 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.8344. Min Act: -0.1700
Data Index: 5284576 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.8032. Min Act: -0.1700
Data Index: 265763 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7719. Min Act: -0.1700
Data Index: 5670000 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7719. Min Act: -0.1700
Data Index: 3690060 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7719. Min Act: -0.1700
Data Index: 8727319 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7719. Min Act: -0.1700
Data Index: 7484026 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7719. Min Act: -0.1700
Data Index: 1620804 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7407. Min Act: -0.1700
Data Index: 6567018 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7407. Min Act: -0.1700
Data Index: 4202770 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7407. Min Act: -0.1700
Data Index: 7225916 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2719. Min Range: -7.2719
Max Act: 6.7407. Min Act: -0.1700
Data Index: 4408531 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19