Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1022. Min Range: -5.1022
Max Act: 5.1022. Min Act: -0.1700
Data Index: 567428 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1022. Min Range: -5.1022
Max Act: 5.0084. Min Act: -0.1700
Data Index: 2424037 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.9772. Min Act: -0.1700
Data Index: 223607 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.9459. Min Act: -0.1700
Data Index: 516434 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.9459. Min Act: -0.1700
Data Index: 7363544 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8834. Min Act: -0.1700
Data Index: 770963 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8834. Min Act: -0.1700
Data Index: 4724825 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8522. Min Act: -0.1700
Data Index: 3482337 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8834. Min Act: -0.1700
Data Index: 4876126 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8834. Min Act: -0.1700
Data Index: 1289863 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8834. Min Act: -0.1700
Data Index: 968804 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8522. Min Act: -0.1700
Data Index: 252331 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8209. Min Act: -0.1700
Data Index: 3538327 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8522. Min Act: -0.1700
Data Index: 4695849 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8209. Min Act: -0.1700
Data Index: 614881 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8209. Min Act: -0.1700
Data Index: 7846095 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.7897. Min Act: -0.1700
Data Index: 1572060 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8209. Min Act: -0.1700
Data Index: 4923478 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.8209. Min Act: -0.1700
Data Index: 8479795 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1022. Min Range: -5.1022
Max Act: 4.7897. Min Act: -0.1700
Data Index: 2538518 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19