Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2181 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.7656. Min Act: -0.1700
Data Index: 3630687 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.2656. Min Act: -0.1700
Data Index: 469871 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.2656. Min Act: -0.1700
Data Index: 1843492 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.2343. Min Act: -0.1700
Data Index: 4589567 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.2031. Min Act: -0.1700
Data Index: 6582782 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.2031. Min Act: -0.1700
Data Index: 8551004 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.2031. Min Act: -0.1700
Data Index: 2484709 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.1406. Min Act: -0.1700
Data Index: 1629901 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.1093. Min Act: -0.1700
Data Index: 4061387 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.0781. Min Act: -0.1700
Data Index: 199331 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.0781. Min Act: -0.1700
Data Index: 998148 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.0781. Min Act: -0.1700
Data Index: 998143 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.0781. Min Act: -0.1700
Data Index: 8388328 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7656. Min Range: -7.7656
Max Act: 7.0156. Min Act: -0.1700
Data Index: 8018671 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7656. Min Range: -7.7656
Max Act: 6.9843. Min Act: -0.1700
Data Index: 3519498 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7656. Min Range: -7.7656
Max Act: 6.9843. Min Act: -0.1700
Data Index: 1273767 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7656. Min Range: -7.7656
Max Act: 6.9843. Min Act: -0.1700
Data Index: 8782106 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7656. Min Range: -7.7656
Max Act: 6.9531. Min Act: -0.1700
Data Index: 2550544 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7656. Min Range: -7.7656
Max Act: 6.9531. Min Act: -0.1700
Data Index: 6352650 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7656. Min Range: -7.7656
Max Act: 6.9531. Min Act: -0.1700
Data Index: 6582786 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19