Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.7521. Min Act: -0.1700
Data Index: 8815650 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.7208. Min Act: -0.1700
Data Index: 3954226 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.7208. Min Act: -0.1698
Data Index: 5895040 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.6896. Min Act: -0.1700
Data Index: 2456696 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.6896. Min Act: -0.1700
Data Index: 4116609 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.6583. Min Act: -0.1700
Data Index: 2504157 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5958. Min Act: -0.1700
Data Index: 6339843 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5646. Min Act: -0.1700
Data Index: 1912130 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5958. Min Act: -0.1700
Data Index: 6267957 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5333. Min Act: -0.1699
Data Index: 5748041 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5333. Min Act: -0.1700
Data Index: 2088295 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5333. Min Act: -0.1700
Data Index: 8540276 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5021. Min Act: -0.1700
Data Index: 8350568 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.4708. Min Act: -0.1700
Data Index: 3337152 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.4396. Min Act: -0.1700
Data Index: 4335396 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.4396. Min Act: -0.1700
Data Index: 1963479 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.5021. Min Act: -0.1700
Data Index: 2504159 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.4708. Min Act: -0.1700
Data Index: 1059080 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.4396. Min Act: -0.1700
Data Index: 7896168 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7521. Min Range: -6.7521
Max Act: 6.4083. Min Act: -0.1700
Data Index: 7917415 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19