Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5228 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4814. Min Range: -5.4814
Max Act: 5.4814. Min Act: -0.1700
Data Index: 1502310 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4814. Min Range: -5.4814
Max Act: 5.2939. Min Act: -0.1700
Data Index: 8106178 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4814. Min Range: -5.4814
Max Act: 5.2001. Min Act: -0.1700
Data Index: 5425048 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4814. Min Range: -5.4814
Max Act: 5.1689. Min Act: -0.1700
Data Index: 36121 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4814. Min Range: -5.4814
Max Act: 5.0751. Min Act: -0.1700
Data Index: 2326333 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4814. Min Range: -5.4814
Max Act: 5.0439. Min Act: -0.1700
Data Index: 7389448 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4814. Min Range: -5.4814
Max Act: 5.0126. Min Act: -0.1700
Data Index: 5876400 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.9814. Min Act: -0.1700
Data Index: 7907973 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.9814. Min Act: -0.1700
Data Index: 8681118 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.9189. Min Act: -0.1700
Data Index: 3393771 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.9189. Min Act: -0.1700
Data Index: 5714363 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.9189. Min Act: -0.1700
Data Index: 1068928 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.8564. Min Act: -0.1700
Data Index: 484338 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.8564. Min Act: -0.1700
Data Index: 4721113 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.8564. Min Act: -0.1700
Data Index: 4128045 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.8564. Min Act: -0.1700
Data Index: 1644041 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.8251. Min Act: -0.1700
Data Index: 8446376 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.8251. Min Act: -0.1700
Data Index: 4089398 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.7939. Min Act: -0.1700
Data Index: 5664590 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4814. Min Range: -5.4814
Max Act: 4.7626. Min Act: -0.1700
Data Index: 4516195 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19