Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7879. Min Act: -0.1700
Data Index: 1797260 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6942. Min Act: -0.1700
Data Index: 7205996 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6629. Min Act: -0.1700
Data Index: 2979325 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6004. Min Act: -0.1700
Data Index: 3305016 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5692. Min Act: -0.1700
Data Index: 5524268 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5692. Min Act: -0.1700
Data Index: 2542412 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5692. Min Act: -0.1700
Data Index: 4025518 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5692. Min Act: -0.1700
Data Index: 4250405 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5692. Min Act: -0.1700
Data Index: 3386413 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6004. Min Act: -0.1700
Data Index: 5426217 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5379. Min Act: -0.1700
Data Index: 190271 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5379. Min Act: -0.1700
Data Index: 1435008 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5067. Min Act: -0.1700
Data Index: 8707696 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5067. Min Act: -0.1700
Data Index: 2485150 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5067. Min Act: -0.1700
Data Index: 176504 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5067. Min Act: -0.1700
Data Index: 8096497 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.4754. Min Act: -0.1700
Data Index: 3711700 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.4442. Min Act: -0.1700
Data Index: 6986843 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.4754. Min Act: -0.1700
Data Index: 2850795 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.4754. Min Act: -0.1700
Data Index: 913055 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19