Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.6868. Min Act: -0.1700
Data Index: 4050700 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.5618. Min Act: -0.1700
Data Index: 1264655 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.5305. Min Act: -0.1700
Data Index: 4868597 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.4993. Min Act: -0.1700
Data Index: 4676961 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.3118. Min Act: -0.1700
Data Index: 4194431 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.2493. Min Act: -0.1699
Data Index: 261965 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.2493. Min Act: -0.1700
Data Index: 1597723 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.1555. Min Act: -0.1700
Data Index: 5218973 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.1243. Min Act: -0.1700
Data Index: 7575275 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.1243. Min Act: -0.1700
Data Index: 1964488 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.1243. Min Act: -0.1700
Data Index: 729113 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.1243. Min Act: -0.1700
Data Index: 5957841 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.1243. Min Act: -0.1700
Data Index: 7627531 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.0930. Min Act: -0.1700
Data Index: 2311339 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.0930. Min Act: -0.1700
Data Index: 6352029 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.0930. Min Act: -0.1700
Data Index: 5076118 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.0930. Min Act: -0.1700
Data Index: 7139001 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.0930. Min Act: -0.1700
Data Index: 4747893 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.0305. Min Act: -0.1700
Data Index: 5218974 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6868. Min Range: -6.6868
Max Act: 6.0618. Min Act: -0.1700
Data Index: 1805119 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19