Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.5389. Min Act: -0.1700
Data Index: 3912692 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4763. Min Act: -0.1700
Data Index: 3859012 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4763. Min Act: -0.1700
Data Index: 5267591 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3328684 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4449. Min Act: -0.1700
Data Index: 5929017 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4136. Min Act: -0.1700
Data Index: 6826544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4136. Min Act: -0.1700
Data Index: 557739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4136. Min Act: -0.1700
Data Index: 3321834 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4136. Min Act: -0.1700
Data Index: 3306864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 3671918 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 7281841 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 7144861 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 6708147 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 3306115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 507800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 5337973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 5300309 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 4668731 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 2983003 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3822. Min Act: -0.1700
Data Index: 2631796 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19