Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.3304. Min Act: -0.1700
Data Index: 5072929 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2991. Min Act: -0.1700
Data Index: 913363 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2366. Min Act: -0.1700
Data Index: 6474507 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2366. Min Act: -0.1700
Data Index: 3075556 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2054. Min Act: -0.1700
Data Index: 6002206 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1741. Min Act: -0.1700
Data Index: 60543 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1741. Min Act: -0.1700
Data Index: 5935982 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1741. Min Act: -0.1700
Data Index: 6171074 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1741. Min Act: -0.1700
Data Index: 3621451 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1429. Min Act: -0.1700
Data Index: 4735548 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1429. Min Act: -0.1700
Data Index: 1964201 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1429. Min Act: -0.1700
Data Index: 4471016 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1429. Min Act: -0.1700
Data Index: 1329733 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1116. Min Act: -0.1700
Data Index: 2963423 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1116. Min Act: -0.1700
Data Index: 4653160 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1429. Min Act: -0.1700
Data Index: 1149450 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1116. Min Act: -0.1700
Data Index: 1265545 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1116. Min Act: -0.1700
Data Index: 2297729 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1116. Min Act: -0.1700
Data Index: 5008533 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1116. Min Act: -0.1700
Data Index: 436900 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19