Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2471 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.6472. Min Act: -0.1700
Data Index: 3900502 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.4597. Min Act: -0.1700
Data Index: 5165792 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.4597. Min Act: -0.1700
Data Index: 5179446 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.3972. Min Act: -0.1700
Data Index: 7890105 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.2097. Min Act: -0.1700
Data Index: 8172947 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.2722. Min Act: -0.1700
Data Index: 3539535 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.2097. Min Act: -0.1700
Data Index: 6683382 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.2722. Min Act: -0.1700
Data Index: 4965822 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.2097. Min Act: -0.1700
Data Index: 7962407 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.1472. Min Act: -0.1700
Data Index: 3106482 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.1160. Min Act: -0.1700
Data Index: 6643950 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.1160. Min Act: -0.1700
Data Index: 4429844 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.1472. Min Act: -0.1700
Data Index: 5870226 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.1160. Min Act: -0.1700
Data Index: 7771428 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.0847. Min Act: -0.1700
Data Index: 2186900 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.0847. Min Act: -0.1700
Data Index: 3301406 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.0535. Min Act: -0.1700
Data Index: 4796728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.0535. Min Act: -0.1700
Data Index: 1768794 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.0222. Min Act: -0.1700
Data Index: 5082829 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6472. Min Range: -8.6472
Max Act: 8.0222. Min Act: -0.1700
Data Index: 1123756 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19