Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.3617. Min Act: -0.1700
Data Index: 3655444 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.3305. Min Act: -0.1700
Data Index: 7183673 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.3305. Min Act: -0.1700
Data Index: 3779356 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.3617. Min Act: -0.1700
Data Index: 3419143 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2992. Min Act: -0.1700
Data Index: 1066816 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2680. Min Act: -0.1700
Data Index: 7183670 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2367. Min Act: -0.1700
Data Index: 7183674 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2367. Min Act: -0.1700
Data Index: 5362257 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2367. Min Act: -0.1700
Data Index: 3690551 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2367. Min Act: -0.1700
Data Index: 8059716 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2367. Min Act: -0.1700
Data Index: 1818067 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2367. Min Act: -0.1700
Data Index: 2703676 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2055. Min Act: -0.1700
Data Index: 1770139 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2055. Min Act: -0.1700
Data Index: 7183676 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2055. Min Act: -0.1700
Data Index: 3059337 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2055. Min Act: -0.1700
Data Index: 610310 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2367. Min Act: -0.1700
Data Index: 3096721 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2055. Min Act: -0.1700
Data Index: 3294172 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1742. Min Act: -0.1700
Data Index: 5567542 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1742. Min Act: -0.1700
Data Index: 4181881 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19