Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1816. Min Range: -3.1816
Max Act: 3.1816. Min Act: -0.1700
Data Index: 4779024 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1816. Min Range: -3.1816
Max Act: 3.1187. Min Act: -0.1700
Data Index: 561672 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1816. Min Range: -3.1816
Max Act: 3.0871. Min Act: -0.1700
Data Index: 680920 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1816. Min Range: -3.1816
Max Act: 3.0714. Min Act: -0.1700
Data Index: 2514068 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1816. Min Range: -3.1816
Max Act: 3.0082. Min Act: -0.1700
Data Index: 404407 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1816. Min Range: -3.1816
Max Act: 3.0082. Min Act: -0.1700
Data Index: 6848007 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9766. Min Act: -0.1700
Data Index: 4368881 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9608. Min Act: -0.1700
Data Index: 6118060 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9608. Min Act: -0.1700
Data Index: 5991588 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9450. Min Act: -0.1700
Data Index: 794594 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9450. Min Act: -0.1700
Data Index: 5710674 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9291. Min Act: -0.1700
Data Index: 4194297 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9291. Min Act: -0.1700
Data Index: 1209119 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9133. Min Act: -0.1700
Data Index: 6801064 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.8974. Min Act: -0.1700
Data Index: 6421787 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9133. Min Act: -0.1700
Data Index: 5730733 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.9133. Min Act: -0.1700
Data Index: 4204876 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.8974. Min Act: -0.1700
Data Index: 1004032 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.8974. Min Act: -0.1700
Data Index: 8542517 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1816. Min Range: -3.1816
Max Act: 2.8816. Min Act: -0.1700
Data Index: 4954340 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19