Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.6521. Min Act: -0.1700
Data Index: 6745301 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.6521. Min Act: -0.1700
Data Index: 3442195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.6521. Min Act: -0.1700
Data Index: 8794843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.4958. Min Act: -0.1700
Data Index: 4420476 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.4646. Min Act: -0.1700
Data Index: 4221863 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.4646. Min Act: -0.1700
Data Index: 1697194 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.4021. Min Act: -0.1700
Data Index: 6289954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.4021. Min Act: -0.1700
Data Index: 7069931 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.4021. Min Act: -0.1700
Data Index: 397037 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.3396. Min Act: -0.1700
Data Index: 1141999 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.3708. Min Act: -0.1700
Data Index: 900132 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.3083. Min Act: -0.1700
Data Index: 1584657 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.2771. Min Act: -0.1700
Data Index: 7559619 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.2771. Min Act: -0.1700
Data Index: 5643561 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.2458. Min Act: -0.1700
Data Index: 1598040 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.2146. Min Act: -0.1700
Data Index: 3133862 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.2146. Min Act: -0.1700
Data Index: 3645990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.2146. Min Act: -0.1700
Data Index: 4142581 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.1833. Min Act: -0.1700
Data Index: 756516 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6521. Min Range: -6.6521
Max Act: 6.1833. Min Act: -0.1700
Data Index: 4624786 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19