Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3008. Min Range: -7.3008
Max Act: 7.3008. Min Act: -0.1700
Data Index: 2821850 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3008. Min Range: -7.3008
Max Act: 7.0821. Min Act: -0.1700
Data Index: 6151258 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3008. Min Range: -7.3008
Max Act: 7.0821. Min Act: -0.1700
Data Index: 7123117 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3008. Min Range: -7.3008
Max Act: 7.0196. Min Act: -0.1700
Data Index: 5299974 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.9883. Min Act: -0.1700
Data Index: 6110645 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.9883. Min Act: -0.1700
Data Index: 2704973 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.9258. Min Act: -0.1700
Data Index: 2082116 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.9258. Min Act: -0.1700
Data Index: 8352298 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.8946. Min Act: -0.1700
Data Index: 1373672 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.8946. Min Act: -0.1700
Data Index: 1854125 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.8946. Min Act: -0.1700
Data Index: 4882922 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.8633. Min Act: -0.1700
Data Index: 5837350 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.8321. Min Act: -0.1700
Data Index: 129205 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.7696. Min Act: -0.1700
Data Index: 7209595 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5598983 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.7383. Min Act: -0.1700
Data Index: 7148374 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.7383. Min Act: -0.1700
Data Index: 5016082 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.7383. Min Act: -0.1700
Data Index: 2143619 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5961301 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3008. Min Range: -7.3008
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5219885 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19