Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4688. Min Range: -4.4688
Max Act: 4.4688. Min Act: -0.1700
Data Index: 1609912 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4688. Min Range: -4.4688
Max Act: 4.1251. Min Act: -0.1700
Data Index: 6863329 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4688. Min Range: -4.4688
Max Act: 4.0000. Min Act: -0.1700
Data Index: 8067722 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4688. Min Range: -4.4688
Max Act: 4.0000. Min Act: -0.1700
Data Index: 8488863 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4688. Min Range: -4.4688
Max Act: 4.0000. Min Act: -0.1700
Data Index: 3014535 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9688. Min Act: -0.1700
Data Index: 1217751 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9688. Min Act: -0.1700
Data Index: 2417302 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9688. Min Act: -0.1700
Data Index: 8594111 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9688. Min Act: -0.1700
Data Index: 2020476 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9688. Min Act: -0.1700
Data Index: 8282730 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9062. Min Act: -0.1700
Data Index: 4526047 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9375. Min Act: -0.1700
Data Index: 6203407 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.9062. Min Act: -0.1700
Data Index: 2584273 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.8750. Min Act: -0.1700
Data Index: 564951 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.8750. Min Act: -0.1700
Data Index: 4664135 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.8750. Min Act: -0.1700
Data Index: 3484267 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.8750. Min Act: -0.1700
Data Index: 2224675 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.8750. Min Act: -0.1700
Data Index: 1996139 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.8750. Min Act: -0.1700
Data Index: 7930141 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4688. Min Range: -4.4688
Max Act: 3.8437. Min Act: -0.1700
Data Index: 1434747 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19