Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.5118. Min Act: -0.1700
Data Index: 1557297 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.3556. Min Act: -0.1700
Data Index: 4611765 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.3243. Min Act: -0.1700
Data Index: 5819807 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.2618. Min Act: -0.1700
Data Index: 2291198 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.2931. Min Act: -0.1700
Data Index: 8759111 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.2618. Min Act: -0.1700
Data Index: 6046494 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.2618. Min Act: -0.1700
Data Index: 8213928 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.2306. Min Act: -0.1700
Data Index: 1021669 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.2306. Min Act: -0.1700
Data Index: 811304 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.2306. Min Act: -0.1700
Data Index: 7065791 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1993. Min Act: -0.1700
Data Index: 7458065 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1993. Min Act: -0.1700
Data Index: 691446 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1681. Min Act: -0.1700
Data Index: 1616012 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1681. Min Act: -0.1700
Data Index: 7970055 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1681. Min Act: -0.1698
Data Index: 1154565 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1681. Min Act: -0.1700
Data Index: 7447953 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5423984 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1681. Min Act: -0.1700
Data Index: 3699558 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1368. Min Act: -0.1700
Data Index: 3491154 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5118. Min Range: -5.5118
Max Act: 5.1368. Min Act: -0.1700
Data Index: 7117629 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19