Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.8901. Min Act: -0.1700
Data Index: 142578 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.6713. Min Act: -0.1700
Data Index: 2544234 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.6401. Min Act: -0.1700
Data Index: 827725 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.6401. Min Act: -0.1700
Data Index: 844140 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.6088. Min Act: -0.1700
Data Index: 6163630 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.6088. Min Act: -0.1700
Data Index: 4431685 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.5463. Min Act: -0.1700
Data Index: 1134983 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.4838. Min Act: -0.1700
Data Index: 7267867 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.4526. Min Act: -0.1700
Data Index: 2422978 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.4838. Min Act: -0.1700
Data Index: 3352280 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.4838. Min Act: -0.1700
Data Index: 6344286 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.4526. Min Act: -0.1700
Data Index: 5619917 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.4526. Min Act: -0.1700
Data Index: 4595391 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.4526. Min Act: -0.1700
Data Index: 1319909 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.3901. Min Act: -0.1700
Data Index: 5983702 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.3901. Min Act: -0.1700
Data Index: 7835955 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.3901. Min Act: -0.1700
Data Index: 4331628 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.3901. Min Act: -0.1700
Data Index: 2479927 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.3901. Min Act: -0.1700
Data Index: 7544374 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8901. Min Range: -7.8901
Max Act: 7.3901. Min Act: -0.1700
Data Index: 3425503 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19