Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.5777. Min Act: -0.1700
Data Index: 2122667 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.4524. Min Act: -0.1700
Data Index: 2921911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.4524. Min Act: -0.1700
Data Index: 6237252 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.4524. Min Act: -0.1700
Data Index: 1191363 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.4524. Min Act: -0.1700
Data Index: 8670067 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.4211. Min Act: -0.1700
Data Index: 4776275 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3897. Min Act: -0.1700
Data Index: 7574344 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3897. Min Act: -0.1700
Data Index: 8007557 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.4211. Min Act: -0.1700
Data Index: 1016554 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3897. Min Act: -0.1700
Data Index: 4685388 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3740. Min Act: -0.1700
Data Index: 2300122 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3740. Min Act: -0.1700
Data Index: 3567431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3740. Min Act: -0.1700
Data Index: 4220677 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3583. Min Act: -0.1700
Data Index: 1608090 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3583. Min Act: -0.1700
Data Index: 1751083 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3427. Min Act: -0.1700
Data Index: 1440380 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3427. Min Act: -0.1700
Data Index: 4609684 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3427. Min Act: -0.1700
Data Index: 5507223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3270. Min Act: -0.1700
Data Index: 5489187 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5777. Min Range: -3.5777
Max Act: 3.3270. Min Act: -0.1700
Data Index: 5847590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19