Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.8633. Min Act: -0.1700
Data Index: 203201 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.8321. Min Act: -0.1700
Data Index: 746066 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.7696. Min Act: -0.1700
Data Index: 8631872 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.8008. Min Act: -0.1700
Data Index: 3041727 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.7383. Min Act: -0.1700
Data Index: 2107826 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.7383. Min Act: -0.1700
Data Index: 5918993 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.7071. Min Act: -0.1700
Data Index: 1243610 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 7421756 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.7071. Min Act: -0.1700
Data Index: 1554499 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 5820676 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 6839837 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 5815010 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6446. Min Act: -0.1700
Data Index: 3903571 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6446. Min Act: -0.1700
Data Index: 5181343 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6133. Min Act: -0.1700
Data Index: 5119661 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6446. Min Act: -0.1700
Data Index: 3106631 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 6527172 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6446. Min Act: -0.1700
Data Index: 4375692 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6758. Min Act: -0.1700
Data Index: 1554500 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8633. Min Range: -6.8633
Max Act: 6.6133. Min Act: -0.1700
Data Index: 203202 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19