Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2095 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.8341. Min Act: -0.1700
Data Index: 8518951 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.8029. Min Act: -0.1700
Data Index: 7035013 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7716. Min Act: -0.1700
Data Index: 7141448 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7716. Min Act: -0.1700
Data Index: 7643451 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7404. Min Act: -0.1700
Data Index: 1878903 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7404. Min Act: -0.1700
Data Index: 5948966 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7091. Min Act: -0.1700
Data Index: 4961617 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7091. Min Act: -0.1700
Data Index: 8634067 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7091. Min Act: -0.1700
Data Index: 1994599 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6779. Min Act: -0.1700
Data Index: 3452424 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6779. Min Act: -0.1700
Data Index: 2296953 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6466. Min Act: -0.1700
Data Index: 6286019 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6466. Min Act: -0.1700
Data Index: 8296775 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6154. Min Act: -0.1700
Data Index: 5422040 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5841. Min Act: -0.1700
Data Index: 6789434 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6154. Min Act: -0.1700
Data Index: 8820141 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5841. Min Act: -0.1700
Data Index: 7376754 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5841. Min Act: -0.1700
Data Index: 6378003 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5529. Min Act: -0.1700
Data Index: 1324139 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5529. Min Act: -0.1700
Data Index: 6552357 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19