Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.9627. Min Act: -0.1700
Data Index: 7806348 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.8690. Min Act: -0.1700
Data Index: 2549937 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.8690. Min Act: -0.1700
Data Index: 4870581 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.7127. Min Act: -0.1700
Data Index: 4948060 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.6815. Min Act: -0.1700
Data Index: 6063079 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.6502. Min Act: -0.1700
Data Index: 5131849 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.6190. Min Act: -0.1700
Data Index: 5131857 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.6190. Min Act: -0.1700
Data Index: 5500361 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5877. Min Act: -0.1700
Data Index: 8017775 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5952982 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5850356 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4653906 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5877. Min Act: -0.1700
Data Index: 1334792 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.6190. Min Act: -0.1700
Data Index: 4948056 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5877. Min Act: -0.1700
Data Index: 6248347 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5565. Min Act: -0.1700
Data Index: 5517904 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5565. Min Act: -0.1700
Data Index: 5275148 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5565. Min Act: -0.1700
Data Index: 5238310 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5565. Min Act: -0.1700
Data Index: 7995631 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9627. Min Range: -5.9627
Max Act: 5.5252. Min Act: -0.1700
Data Index: 5554665 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19