Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.3616. Min Act: -0.1700
Data Index: 6872345 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2991. Min Act: -0.1700
Data Index: 4246230 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2678. Min Act: -0.1700
Data Index: 2180007 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2366. Min Act: -0.1700
Data Index: 4637318 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2366. Min Act: -0.1700
Data Index: 7991024 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2053. Min Act: -0.1700
Data Index: 4853977 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2366. Min Act: -0.1700
Data Index: 3509082 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2366. Min Act: -0.1700
Data Index: 8735654 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2053. Min Act: -0.1700
Data Index: 5974250 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2053. Min Act: -0.1700
Data Index: 7035453 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2053. Min Act: -0.1700
Data Index: 1757389 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2053. Min Act: -0.1700
Data Index: 4940132 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1741. Min Act: -0.1700
Data Index: 1668481 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1741. Min Act: -0.1700
Data Index: 7612398 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1741. Min Act: -0.1700
Data Index: 5461169 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1428. Min Act: -0.1700
Data Index: 8661411 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1116. Min Act: -0.1700
Data Index: 6679149 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1428. Min Act: -0.1700
Data Index: 7492403 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1116. Min Act: -0.1700
Data Index: 8661403 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1116. Min Act: -0.1700
Data Index: 8711905 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19