Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.5874. Min Act: -0.1700
Data Index: 5667534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.2749. Min Act: -0.1700
Data Index: 6354683 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.2124. Min Act: -0.1700
Data Index: 322239 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.2124. Min Act: -0.1700
Data Index: 795698 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1811. Min Act: -0.1700
Data Index: 4711144 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1811. Min Act: -0.1700
Data Index: 5350806 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1499. Min Act: -0.1700
Data Index: 3040594 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1499. Min Act: -0.1700
Data Index: 5732007 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1499. Min Act: -0.1700
Data Index: 975177 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1499. Min Act: -0.1700
Data Index: 3671697 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 8102052 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 5616202 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 8345203 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 1672076 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 490411 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 6749637 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 6676898 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 8054267 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 8502690 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5874. Min Range: -4.5874
Max Act: 4.1186. Min Act: -0.1700
Data Index: 311712 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19