Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 161 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2480. Min Range: -6.2480
Max Act: 6.2480. Min Act: -0.1700
Data Index: 5509539 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.9667. Min Act: -0.1700
Data Index: 2413514 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.8105. Min Act: -0.1700
Data Index: 4000000 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.7480. Min Act: -0.1700
Data Index: 5506749 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.7167. Min Act: -0.1700
Data Index: 5914670 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.6542. Min Act: -0.1700
Data Index: 274284 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.6230. Min Act: -0.1700
Data Index: 7161823 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.5292. Min Act: -0.1700
Data Index: 1694182 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4667. Min Act: -0.1700
Data Index: 62569 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4980. Min Act: -0.1700
Data Index: 1788850 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4980. Min Act: -0.1700
Data Index: 4584687 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4980. Min Act: -0.1700
Data Index: 4454351 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4667. Min Act: -0.1700
Data Index: 5625933 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4667. Min Act: -0.1700
Data Index: 5000767 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4667. Min Act: -0.1700
Data Index: 6232908 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4355. Min Act: -0.1700
Data Index: 8812325 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4355. Min Act: -0.1700
Data Index: 3176545 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4667. Min Act: -0.1700
Data Index: 4000006 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4355. Min Act: -0.1700
Data Index: 1788847 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2480. Min Range: -6.2480
Max Act: 5.4042. Min Act: -0.1700
Data Index: 6042819 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19