Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.7762. Min Act: -0.1700
Data Index: 591410 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.4950. Min Act: -0.1700
Data Index: 6642337 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.4637. Min Act: -0.1700
Data Index: 3667280 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.4012. Min Act: -0.1700
Data Index: 4271313 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.4012. Min Act: -0.1700
Data Index: 5803909 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.3075. Min Act: -0.1700
Data Index: 2652455 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.2762. Min Act: -0.1700
Data Index: 7584923 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.2762. Min Act: -0.1700
Data Index: 1598571 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.2450. Min Act: -0.1700
Data Index: 2465282 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.2450. Min Act: -0.1700
Data Index: 8289094 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.2137. Min Act: -0.1700
Data Index: 4629534 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.2137. Min Act: -0.1700
Data Index: 3984645 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.2137. Min Act: -0.1700
Data Index: 2214104 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.1825. Min Act: -0.1700
Data Index: 4191455 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.1825. Min Act: -0.1700
Data Index: 7589604 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.1512. Min Act: -0.1700
Data Index: 2029497 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.1825. Min Act: -0.1700
Data Index: 7332724 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.1512. Min Act: -0.1700
Data Index: 7636746 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.1512. Min Act: -0.1700
Data Index: 4986689 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7762. Min Range: -7.7762
Max Act: 7.1512. Min Act: -0.1700
Data Index: 1666123 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19