Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5889. Min Range: -7.5889
Max Act: 7.5889. Min Act: -0.1700
Data Index: 2665202 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5889. Min Range: -7.5889
Max Act: 7.5577. Min Act: -0.1700
Data Index: 3771263 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5889. Min Range: -7.5889
Max Act: 7.5264. Min Act: -0.1700
Data Index: 2693035 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5889. Min Range: -7.5889
Max Act: 7.0577. Min Act: -0.1700
Data Index: 5500300 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5889. Min Range: -7.5889
Max Act: 7.0577. Min Act: -0.1700
Data Index: 4681326 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.9952. Min Act: -0.1700
Data Index: 2256616 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.9639. Min Act: -0.1700
Data Index: 6586014 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.9639. Min Act: -0.1700
Data Index: 7778649 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.9639. Min Act: -0.1700
Data Index: 5967738 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.9327. Min Act: -0.1700
Data Index: 895284 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.9327. Min Act: -0.1700
Data Index: 4950778 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.9014. Min Act: -0.1700
Data Index: 7892122 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8702. Min Act: -0.1700
Data Index: 2799512 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8389. Min Act: -0.1700
Data Index: 3276571 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8702. Min Act: -0.1700
Data Index: 5075941 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8702. Min Act: -0.1700
Data Index: 3129318 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8702. Min Act: -0.1700
Data Index: 7053537 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8702. Min Act: -0.1700
Data Index: 778086 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8702. Min Act: -0.1700
Data Index: 1330047 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5889. Min Range: -7.5889
Max Act: 6.8702. Min Act: -0.1700
Data Index: 8621707 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19