Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5372 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0787. Min Act: -0.1700
Data Index: 1876685 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0629. Min Act: -0.1700
Data Index: 4299203 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0313. Min Act: -0.1700
Data Index: 4367006 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0155. Min Act: -0.1700
Data Index: 3714581 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0155. Min Act: -0.1700
Data Index: 546924 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9997. Min Act: -0.1700
Data Index: 842548 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0155. Min Act: -0.1700
Data Index: 6105890 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0155. Min Act: -0.1700
Data Index: 6873863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0155. Min Act: -0.1700
Data Index: 3997104 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0787. Min Range: -3.0787
Max Act: 3.0155. Min Act: -0.1700
Data Index: 3159673 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9997. Min Act: -0.1700
Data Index: 4527244 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9997. Min Act: -0.1700
Data Index: 7496579 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9997. Min Act: -0.1700
Data Index: 2755121 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9997. Min Act: -0.1700
Data Index: 6559774 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9997. Min Act: -0.1700
Data Index: 8676700 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9839. Min Act: -0.1700
Data Index: 6790381 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9839. Min Act: -0.1700
Data Index: 4746302 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9839. Min Act: -0.1700
Data Index: 942603 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9839. Min Act: -0.1700
Data Index: 5361557 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0787. Min Range: -3.0787
Max Act: 2.9839. Min Act: -0.1700
Data Index: 7556329 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19