Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1478 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0909. Min Range: -6.0909
Max Act: 6.0909. Min Act: -0.1700
Data Index: 5375148 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0909. Min Range: -6.0909
Max Act: 6.0284. Min Act: -0.1700
Data Index: 1203509 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0909. Min Range: -6.0909
Max Act: 6.0284. Min Act: -0.1700
Data Index: 4139985 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.9972. Min Act: -0.1700
Data Index: 5615547 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.9972. Min Act: -0.1700
Data Index: 8090888 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.9347. Min Act: -0.1700
Data Index: 7573733 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.8722. Min Act: -0.1700
Data Index: 791093 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.8409. Min Act: -0.1700
Data Index: 1263994 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.8409. Min Act: -0.1700
Data Index: 3344139 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6247325 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.8097. Min Act: -0.1700
Data Index: 7664657 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.8097. Min Act: -0.1700
Data Index: 5158509 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.7784. Min Act: -0.1700
Data Index: 2021075 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.7784. Min Act: -0.1700
Data Index: 4755759 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.7784. Min Act: -0.1700
Data Index: 6157006 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.7784. Min Act: -0.1700
Data Index: 7757147 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.7784. Min Act: -0.1700
Data Index: 3914077 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.8097. Min Act: -0.1700
Data Index: 3469328 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.7784. Min Act: -0.1700
Data Index: 5374091 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0909. Min Range: -6.0909
Max Act: 5.7472. Min Act: -0.1700
Data Index: 5091201 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19