Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5919 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2243. Min Range: -4.2243
Max Act: 4.2243. Min Act: -0.1700
Data Index: 7222938 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2243. Min Range: -4.2243
Max Act: 4.1618. Min Act: -0.1700
Data Index: 83085 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.9742. Min Act: -0.1700
Data Index: 5118689 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.9742. Min Act: -0.1700
Data Index: 6567298 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.9430. Min Act: -0.1700
Data Index: 3700894 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.9117. Min Act: -0.1700
Data Index: 3870692 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.9117. Min Act: -0.1700
Data Index: 2351919 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 7043398 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 493712 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 1414191 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 5119723 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 6191250 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 619591 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 6595036 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8492. Min Act: -0.1700
Data Index: 6677539 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8492. Min Act: -0.1700
Data Index: 3379058 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8492. Min Act: -0.1700
Data Index: 865545 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8804. Min Act: -0.1700
Data Index: 5999865 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.7866. Min Act: -0.1700
Data Index: 1321993 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2243. Min Range: -4.2243
Max Act: 3.8179. Min Act: -0.1700
Data Index: 5210459 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19