Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1934 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0092. Min Range: -3.0092
Max Act: 3.0092. Min Act: -0.1700
Data Index: 4080268 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.9934. Min Act: -0.1700
Data Index: 4801816 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.9776. Min Act: -0.1700
Data Index: 6193404 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8984. Min Act: -0.1700
Data Index: 8239695 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8984. Min Act: -0.1700
Data Index: 4090771 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8984. Min Act: -0.1700
Data Index: 1557191 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8984. Min Act: -0.1700
Data Index: 4607278 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8667. Min Act: -0.1700
Data Index: 3866947 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8667. Min Act: -0.1700
Data Index: 4681121 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8508. Min Act: -0.1700
Data Index: 4238552 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8508. Min Act: -0.1700
Data Index: 4051109 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8508. Min Act: -0.1700
Data Index: 1444016 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8349. Min Act: -0.1700
Data Index: 2905513 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8349. Min Act: -0.1700
Data Index: 2605148 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8190. Min Act: -0.1700
Data Index: 8446486 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8031. Min Act: -0.1700
Data Index: 1132486 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.7872. Min Act: -0.1700
Data Index: 6129735 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8031. Min Act: -0.1700
Data Index: 6818147 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.8031. Min Act: -0.1700
Data Index: 3887124 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0092. Min Range: -3.0092
Max Act: 2.7712. Min Act: -0.1700
Data Index: 3057725 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19