Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 717 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0581. Min Range: -7.0581
Max Act: 7.0581. Min Act: -0.1700
Data Index: 1563752 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.8393. Min Act: -0.1700
Data Index: 8287647 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.8081. Min Act: -0.1700
Data Index: 4622710 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.6518. Min Act: -0.1700
Data Index: 1106502 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.6206. Min Act: -0.1700
Data Index: 331809 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.5893. Min Act: -0.1700
Data Index: 3764599 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.5581. Min Act: -0.1700
Data Index: 8092505 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.4643. Min Act: -0.1700
Data Index: 3592443 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.4331. Min Act: -0.1700
Data Index: 7098754 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.4018. Min Act: -0.1700
Data Index: 4796982 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.4331. Min Act: -0.1700
Data Index: 1982335 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.4018. Min Act: -0.1700
Data Index: 4807154 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.4018. Min Act: -0.1700
Data Index: 4693047 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.3706. Min Act: -0.1700
Data Index: 715440 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.3706. Min Act: -0.1700
Data Index: 2419212 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.3393. Min Act: -0.1700
Data Index: 1877962 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.3393. Min Act: -0.1700
Data Index: 8070082 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.3081. Min Act: -0.1700
Data Index: 7824281 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.3081. Min Act: -0.1700
Data Index: 7653092 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0581. Min Range: -7.0581
Max Act: 6.3081. Min Act: -0.1700
Data Index: 478855 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19