Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8788. Min Range: -7.8788
Max Act: 7.8788. Min Act: -0.1700
Data Index: 3512782 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8788. Min Range: -7.8788
Max Act: 7.2850. Min Act: -0.1700
Data Index: 6803732 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8788. Min Range: -7.8788
Max Act: 7.1600. Min Act: -0.1700
Data Index: 214474 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8788. Min Range: -7.8788
Max Act: 7.0663. Min Act: -0.1700
Data Index: 1622367 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8788. Min Range: -7.8788
Max Act: 7.0038. Min Act: -0.1700
Data Index: 1622366 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8788. Min Range: -7.8788
Max Act: 7.0038. Min Act: -0.1700
Data Index: 3319761 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.9725. Min Act: -0.1700
Data Index: 5826000 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.9413. Min Act: -0.1700
Data Index: 1762912 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 1312829 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 6514808 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.8475. Min Act: -0.1700
Data Index: 214472 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.7850. Min Act: -0.1700
Data Index: 5263469 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.7850. Min Act: -0.1700
Data Index: 6432036 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.7225. Min Act: -0.1700
Data Index: 1622368 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.7225. Min Act: -0.1700
Data Index: 3319764 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.6913. Min Act: -0.1700
Data Index: 1150047 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.6913. Min Act: -0.1700
Data Index: 1933538 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.6913. Min Act: -0.1700
Data Index: 5727174 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.6913. Min Act: -0.1700
Data Index: 1947551 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8788. Min Range: -7.8788
Max Act: 6.6600. Min Act: -0.1700
Data Index: 2638843 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19