Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.7374. Min Act: -0.1700
Data Index: 3943034 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.7374. Min Act: -0.1700
Data Index: 7818063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6749. Min Act: -0.1700
Data Index: 6007322 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6749. Min Act: -0.1700
Data Index: 3449728 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6749. Min Act: -0.1700
Data Index: 2797696 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 3124397 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 3136674 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1699
Data Index: 2374798 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 663310 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 375772 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 1592482 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1670
Data Index: 1592589 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 2464157 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 3331444 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 958446 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 1861113 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 919672 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1696
Data Index: 2010518 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1700
Data Index: 3611687 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7374. Min Range: -4.7374
Max Act: 4.6436. Min Act: -0.1699
Data Index: 1540554 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19