Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1845 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.4579. Min Act: -0.1700
Data Index: 5649148 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3017. Min Act: -0.1700
Data Index: 5695787 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3017. Min Act: -0.1700
Data Index: 5848911 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3017. Min Act: -0.1700
Data Index: 4115061 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2704. Min Act: -0.1700
Data Index: 5186188 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2079. Min Act: -0.1700
Data Index: 8559735 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2079. Min Act: -0.1700
Data Index: 5795610 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1767. Min Act: -0.1700
Data Index: 6352313 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1767. Min Act: -0.1700
Data Index: 4325133 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1454. Min Act: -0.1700
Data Index: 232224 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1454. Min Act: -0.1700
Data Index: 3657748 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1454. Min Act: -0.1700
Data Index: 958234 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1454. Min Act: -0.1700
Data Index: 6679154 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1142. Min Act: -0.1700
Data Index: 4880072 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1142. Min Act: -0.1700
Data Index: 4129604 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1142. Min Act: -0.1700
Data Index: 3447233 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.1142. Min Act: -0.1700
Data Index: 7869708 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.0829. Min Act: -0.1700
Data Index: 345784 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.0829. Min Act: -0.1700
Data Index: 7527428 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.0829. Min Act: -0.1700
Data Index: 384292 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19