Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 897 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.7403. Min Act: -0.1700
Data Index: 5497229 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.6153. Min Act: -0.1700
Data Index: 4007412 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.6466. Min Act: -0.1700
Data Index: 6901508 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.6153. Min Act: -0.1700
Data Index: 6211431 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.5841. Min Act: -0.1700
Data Index: 7784265 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.5841. Min Act: -0.1700
Data Index: 5090522 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.5528. Min Act: -0.1700
Data Index: 8494750 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.5216. Min Act: -0.1700
Data Index: 4766373 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4903. Min Act: -0.1700
Data Index: 1965557 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.5216. Min Act: -0.1700
Data Index: 2550209 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4591. Min Act: -0.1700
Data Index: 6303994 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4591. Min Act: -0.1700
Data Index: 4882000 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4591. Min Act: -0.1700
Data Index: 6137919 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4278. Min Act: -0.1700
Data Index: 555102 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4278. Min Act: -0.1700
Data Index: 3908074 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4278. Min Act: -0.1700
Data Index: 2526105 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.4278. Min Act: -0.1700
Data Index: 8029608 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.3966. Min Act: -0.1700
Data Index: 6670368 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.3966. Min Act: -0.1700
Data Index: 1074841 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7403. Min Range: -5.7403
Max Act: 5.3653. Min Act: -0.1700
Data Index: 8008227 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19